README

3 years ago · f9332c2b94
--- a/.clang-format
+++ b/.clang-format
@@ -0,0 +1,85 @@
 AccessModifierOffset: -1
 AlignAfterOpenBracket: AlwaysBreak
 AlignConsecutiveAssignments: false
 AlignConsecutiveDeclarations: false
 AlignEscapedNewlinesLeft: true
 AlignOperands:   false
 AlignTrailingComments: false
 AllowAllParametersOfDeclarationOnNextLine: false
 AllowShortBlocksOnASingleLine: false
 AllowShortCaseLabelsOnASingleLine: false
 AllowShortFunctionsOnASingleLine: Empty
 AllowShortIfStatementsOnASingleLine: false
 AllowShortLoopsOnASingleLine: false
 AlwaysBreakAfterReturnType: None
 AlwaysBreakBeforeMultilineStrings: true
 AlwaysBreakTemplateDeclarations: true
 BinPackArguments: false
 BinPackParameters: false
 BraceWrapping:
  AfterClass:      false
  AfterControlStatement: false
  AfterEnum:       false
  AfterFunction:   false
  AfterNamespace:  false
  AfterObjCDeclaration: false
  AfterStruct:     false
  AfterUnion:      false
  BeforeCatch:     false
  BeforeElse:      false
  IndentBraces:    false
 BreakBeforeBinaryOperators: None
 BreakBeforeBraces: Attach
 BreakBeforeTernaryOperators: true
 BreakConstructorInitializersBeforeComma: false
 BreakAfterJavaFieldAnnotations: false
 BreakStringLiterals: false
 ColumnLimit:     80
 CommentPragmas:  '^ IWYU pragma:'
 ConstructorInitializerAllOnOneLineOrOnePerLine: true
 ConstructorInitializerIndentWidth: 4
 ContinuationIndentWidth: 4
 Cpp11BracedListStyle: true
 DerivePointerAlignment: false
 DisableFormat:   false
 ForEachMacros:   [ FOR_EACH, FOR_EACH_ENUMERATE, FOR_EACH_KV, FOR_EACH_R, FOR_EACH_RANGE, ]
 IncludeCategories:
  - Regex:           '^<.*\.h(pp)?>'
    Priority:        1
  - Regex:           '^<.*'
    Priority:        2
  - Regex:           '.*'
    Priority:        3
 IndentCaseLabels: true
 IndentWidth:     2
 IndentWrappedFunctionNames: false
 KeepEmptyLinesAtTheStartOfBlocks: false
 MacroBlockBegin: ''
 MacroBlockEnd:   ''
 MaxEmptyLinesToKeep: 1
 NamespaceIndentation: None
 ObjCBlockIndentWidth: 2
 ObjCSpaceAfterProperty: false
 ObjCSpaceBeforeProtocolList: false
 PenaltyBreakBeforeFirstCallParameter: 1
 PenaltyBreakComment: 300
 PenaltyBreakFirstLessLess: 120
 PenaltyBreakString: 1000
 PenaltyExcessCharacter: 1000000
 PenaltyReturnTypeOnItsOwnLine: 200
 PointerAlignment: Left
 ReflowComments:  true
 SortIncludes:    true
 SpaceAfterCStyleCast: false
 SpaceBeforeAssignmentOperators: true
 SpaceBeforeParens: ControlStatements
 SpaceInEmptyParentheses: false
 SpacesBeforeTrailingComments: 1
 SpacesInAngles:  false
 SpacesInContainerLiterals: true
 SpacesInCStyleCastParentheses: false
 SpacesInParentheses: false
 SpacesInSquareBrackets: false
 Standard:        Cpp11
 TabWidth:        8
 UseTab:          Never
--- a/.flake8
+++ b/.flake8
@@ -0,0 +1,9 @@
 # This is an example .flake8 config, used when developing *Black* itself.
 # Keep in sync with setup.cfg which is used for source packages.

 [flake8]
 ignore = W503, E203, E221, C901
 max-line-length = 100
 max-complexity = 18
 select = B,C,E,F,W,T4,B9
 exclude = build,__init__.py
--- a/+ 42
+++ b/+ 42
@@ -0,0 +1,42 @@
 FROM nvidia/cuda:10.1-cudnn7-devel
 # To use this Dockerfile:
 # 1. `nvidia-docker build -t detectron2:v0 .`
 # 2. `nvidia-docker run -it --name detectron2 detectron2:v0`
 # 
 # To enable GUI support (Linux):
 # 1. Grant the container temporary access to your x server (will be reverted at reboot of your host): 
 #    `xhost +local:`docker inspect --format='{{ .Config.Hostname }}' detectron2``
 # 2. `nvidia-docker run -it --name detectron2 --env="DISPLAY" --volume="/tmp/.X11-unix:/tmp/.X11-unix:rw" detectron2:v0`


 ENV DEBIAN_FRONTEND noninteractive
 RUN apt-get update && apt-get install -y \
 	libpng-dev libjpeg-dev python3-opencv ca-certificates \
 	python3-dev build-essential pkg-config git curl wget automake libtool && \
  rm -rf /var/lib/apt/lists/*

 RUN curl -fSsL -O https://bootstrap.pypa.io/get-pip.py && \
 	python3 get-pip.py && \
 	rm get-pip.py

 # install dependencies
 # See https://pytorch.org/ for other options if you use a different version of CUDA
 RUN pip install torch torchvision cython \
 	'git+https://github.com/facebookresearch/fvcore'
 RUN pip install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'

 # install detectron2
 RUN git clone https://github.com/facebookresearch/detectron2 /detectron2_repo
 ENV FORCE_CUDA="1"
 ENV TORCH_CUDA_ARCH_LIST="Kepler;Kepler+Tesla;Maxwell;Maxwell+Tegra;Pascal;Volta;Turing"
 RUN pip install -e /detectron2_repo

 WORKDIR /detectron2_repo

 # run it, for example:
 # wget http://images.cocodataset.org/val2017/000000439715.jpg -O input.jpg
 # python3 demo/demo.py  \
 	#--config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
 	#--input input.jpg --output outputs/ \
 	#--opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl

--- a/GETTING_STARTED.md
+++ b/GETTING_STARTED.md
@@ -0,0 +1,79 @@

 ## Getting Started with Detectron2

 This document provides a brief intro of the usage of builtin command-line tools in detectron2.

 For a tutorial that involves actual coding with the API,
 see our [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
 which covers how to run inference with an
 existing model, and how to train a builtin model on a custom dataset.

 For more advanced tutorials, refer to our [documentation](https://detectron2.readthedocs.io/tutorials/extend.html).


 ### Inference with Pre-trained Models

 1. Pick a model and its config file from
 	[model zoo](https://github.com/facebookresearch/detectron2/blob/master/MODEL_ZOO.md),
 	for example, `mask_rcnn_R_50_FPN_3x.yaml`.
 2. Run the demo with
 ```
 python demo/demo.py --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
  --input input1.jpg input2.jpg \
 	[--other-options]
  --opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl
 ```
 The configs are made for training, therefore we need to specify `MODEL.WEIGHTS` to a model from model zoo for evaluation.
 This command will run the inference and show visualizations in an OpenCV window.

 For details of the command line arguments, see `demo.py -h`. Some common ones are:
 * To run __on your webcam__, replace `--input files` with `--webcam`.
 * To run __on a video__, replace `--input files` with `--video-input video.mp4`.
 * To run __on cpu__, add `MODEL.DEVICE cpu` after `--opts`.
 * To save outputs to a directory (for images) or a file (for webcam or video), use `--output`.


 ### Use Detectron2 in Command Line

 We provide a script in "tools/train_net.py", that is made to train
 all the configs provided in detectron2.
 You may want to use it as a reference to write your own training script for a new research.

 To train a model with "train_net.py", first
 setup the corresponding datasets following
 [datasets/README.md](https://github.com/facebookresearch/detectron2/blob/master/datasets/README.md),
 then run:
 ```
 python tools/train_net.py --num-gpus 8 \
 	--config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml
 ```

 The configs are made for 8-GPU training. To train on 1 GPU, change the batch size with:
 ```
 python tools/train_net.py \
 	--config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml \
 	SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025
 ```

 For most models, CPU training is not supported.

 (Note that we applied the [linear learning rate scaling rule](https://arxiv.org/abs/1706.02677)
 when changing the batch size.)

 To evaluate this model's performance, use
 ```
 python tools/train_net.py \
 	--config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml \
 	--eval-only MODEL.WEIGHTS /path/to/checkpoint_file
 ```
 For more options, see `python tools/train_net.py -h`.

 ### Use Detectron2 in Your Code

 See our [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
 to learn how to use detectron2 APIs to:
 1. run inference with an existing model
 2. train a builtin model on a custom dataset

 See [detectron2/projects](https://github.com/facebookresearch/detectron2/tree/master/projects)
 for more ways to build your project on detectron2.
--- a/INSTALL.md
+++ b/INSTALL.md
@@ -0,0 +1,69 @@
 ## Installation

 Our [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
 has step-by-step instructions that install detectron2.
 The [Dockerfile](https://github.com/facebookresearch/detectron2/blob/master/Dockerfile)
 also installs detectron2 with a few simple commands.

 ### Requirements
 - Linux or macOS
 - Python >= 3.6
 - PyTorch 1.3
 - [torchvision](https://github.com/pytorch/vision/) that matches the PyTorch installation.
 	You can install them together at [pytorch.org](https://pytorch.org) to make sure of this.
 - OpenCV, needed by demo and visualization
 - [fvcore](https://github.com/facebookresearch/fvcore/): `pip install git+https://github.com/facebookresearch/fvcore`
 - pycocotools: `pip install cython; pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI`
 - VS2019/CUDA10.1


 ### Build Detectron2

 After having the above dependencies, run:
 ```
 git clone https://github.com/facebookresearch/detectron2.git
 cd detectron2
 python setup.py build develop

 # or if you are on macOS
 # MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ python setup.py build develop

 # or, as an alternative to `setup.py`, do
 # pip install [--editable] .
 ```
 Note: you may need to rebuild detectron2 after reinstalling a different build of PyTorch.

 ### Common Installation Issues

 + Undefined torch/aten symbols, or segmentation fault immediately when running the library.
  This may be caused by the following reasons:

 	* detectron2 or torchvision is not compiled with the version of PyTorch you're running.

 		If you use a pre-built torchvision, uninstall torchvision & pytorch, and reinstall them
 		following [pytorch.org](http://pytorch.org).
 		If you manually build detectron2 or torchvision, remove the files you built (`build/`, `**/*.so`)
 		and rebuild them.

 	* detectron2 or torchvision is not compiled using gcc >= 4.9.

 	  You'll see a warning message during compilation in this case. Please remove the files you build,
 		and rebuild them.
 		Technically, you need the identical compiler that's used to build pytorch to guarantee
 		compatibility. But in practice, gcc >= 4.9 should work OK.

 + Undefined cuda symbols. The version of NVCC you use to build detectron2 or torchvision does
 	not match the version of cuda you are running with.
 	This happens sometimes when using anaconda.

 + "Not compiled with GPU support": make sure
 	```
 	python -c 'import torch; from torch.utils.cpp_extension import CUDA_HOME; print(torch.cuda.is_available(), CUDA_HOME)'
 	```
 	print valid outputs at the time you build detectron2.

 + "invalid device function" or "no kernel image is available for execution": two possibilities:
  * You build detectron2 with one version of CUDA but run it with a different version.
  * Detectron2 is not built with the correct compute compability for the GPU model.
    The compute compability defaults to match the GPU found on the machine during building,
    and can be controlled by `TORCH_CUDA_ARCH_LIST` environment variable during installation.
--- a/+ 199
+++ b/+ 199
@@ -1,5 +1,201 @@
 Copyright (C) YEAR by AUTHOR EMAIL
 Apache License
 Version 2.0, January 2004
 http://www.apache.org/licenses/

 Permission to use, copy, modify, and/or distribute this software for any purpose with or without fee is hereby granted.
 TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

 THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 1. Definitions.

 "License" shall mean the terms and conditions for use, reproduction,
 and distribution as defined by Sections 1 through 9 of this document.

 "Licensor" shall mean the copyright owner or entity authorized by
 the copyright owner that is granting the License.

 "Legal Entity" shall mean the union of the acting entity and all
 other entities that control, are controlled by, or are under common
 control with that entity. For the purposes of this definition,
 "control" means (i) the power, direct or indirect, to cause the
 direction or management of such entity, whether by contract or
 otherwise, or (ii) ownership of fifty percent (50%) or more of the
 outstanding shares, or (iii) beneficial ownership of such entity.

 "You" (or "Your") shall mean an individual or Legal Entity
 exercising permissions granted by this License.

 "Source" form shall mean the preferred form for making modifications,
 including but not limited to software source code, documentation
 source, and configuration files.

 "Object" form shall mean any form resulting from mechanical
 transformation or translation of a Source form, including but
 not limited to compiled object code, generated documentation,
 and conversions to other media types.

 "Work" shall mean the work of authorship, whether in Source or
 Object form, made available under the License, as indicated by a
 copyright notice that is included in or attached to the work
 (an example is provided in the Appendix below).

 "Derivative Works" shall mean any work, whether in Source or Object
 form, that is based on (or derived from) the Work and for which the
 editorial revisions, annotations, elaborations, or other modifications
 represent, as a whole, an original work of authorship. For the purposes
 of this License, Derivative Works shall not include works that remain
 separable from, or merely link (or bind by name) to the interfaces of,
 the Work and Derivative Works thereof.

 "Contribution" shall mean any work of authorship, including
 the original version of the Work and any modifications or additions
 to that Work or Derivative Works thereof, that is intentionally
 submitted to Licensor for inclusion in the Work by the copyright owner
 or by an individual or Legal Entity authorized to submit on behalf of
 the copyright owner. For the purposes of this definition, "submitted"
 means any form of electronic, verbal, or written communication sent
 to the Licensor or its representatives, including but not limited to
 communication on electronic mailing lists, source code control systems,
 and issue tracking systems that are managed by, or on behalf of, the
 Licensor for the purpose of discussing and improving the Work, but
 excluding communication that is conspicuously marked or otherwise
 designated in writing by the copyright owner as "Not a Contribution."

 "Contributor" shall mean Licensor and any individual or Legal Entity
 on behalf of whom a Contribution has been received by Licensor and
 subsequently incorporated within the Work.

 2. Grant of Copyright License. Subject to the terms and conditions of
 this License, each Contributor hereby grants to You a perpetual,
 worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 copyright license to reproduce, prepare Derivative Works of,
 publicly display, publicly perform, sublicense, and distribute the
 Work and such Derivative Works in Source or Object form.

 3. Grant of Patent License. Subject to the terms and conditions of
 this License, each Contributor hereby grants to You a perpetual,
 worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 (except as stated in this section) patent license to make, have made,
 use, offer to sell, sell, import, and otherwise transfer the Work,
 where such license applies only to those patent claims licensable
 by such Contributor that are necessarily infringed by their
 Contribution(s) alone or by combination of their Contribution(s)
 with the Work to which such Contribution(s) was submitted. If You
 institute patent litigation against any entity (including a
 cross-claim or counterclaim in a lawsuit) alleging that the Work
 or a Contribution incorporated within the Work constitutes direct
 or contributory patent infringement, then any patent licenses
 granted to You under this License for that Work shall terminate
 as of the date such litigation is filed.

 4. Redistribution. You may reproduce and distribute copies of the
 Work or Derivative Works thereof in any medium, with or without
 modifications, and in Source or Object form, provided that You
 meet the following conditions:

 (a) You must give any other recipients of the Work or
 Derivative Works a copy of this License; and

 (b) You must cause any modified files to carry prominent notices
 stating that You changed the files; and

 (c) You must retain, in the Source form of any Derivative Works
 that You distribute, all copyright, patent, trademark, and
 attribution notices from the Source form of the Work,
 excluding those notices that do not pertain to any part of
 the Derivative Works; and

 (d) If the Work includes a "NOTICE" text file as part of its
 distribution, then any Derivative Works that You distribute must
 include a readable copy of the attribution notices contained
 within such NOTICE file, excluding those notices that do not
 pertain to any part of the Derivative Works, in at least one
 of the following places: within a NOTICE text file distributed
 as part of the Derivative Works; within the Source form or
 documentation, if provided along with the Derivative Works; or,
 within a display generated by the Derivative Works, if and
 wherever such third-party notices normally appear. The contents
 of the NOTICE file are for informational purposes only and
 do not modify the License. You may add Your own attribution
 notices within Derivative Works that You distribute, alongside
 or as an addendum to the NOTICE text from the Work, provided
 that such additional attribution notices cannot be construed
 as modifying the License.

 You may add Your own copyright statement to Your modifications and
 may provide additional or different license terms and conditions
 for use, reproduction, or distribution of Your modifications, or
 for any such Derivative Works as a whole, provided Your use,
 reproduction, and distribution of the Work otherwise complies with
 the conditions stated in this License.

 5. Submission of Contributions. Unless You explicitly state otherwise,
 any Contribution intentionally submitted for inclusion in the Work
 by You to the Licensor shall be under the terms and conditions of
 this License, without any additional terms or conditions.
 Notwithstanding the above, nothing herein shall supersede or modify
 the terms of any separate license agreement you may have executed
 with Licensor regarding such Contributions.

 6. Trademarks. This License does not grant permission to use the trade
 names, trademarks, service marks, or product names of the Licensor,
 except as required for reasonable and customary use in describing the
 origin of the Work and reproducing the content of the NOTICE file.

 7. Disclaimer of Warranty. Unless required by applicable law or
 agreed to in writing, Licensor provides the Work (and each
 Contributor provides its Contributions) on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
 implied, including, without limitation, any warranties or conditions
 of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
 PARTICULAR PURPOSE. You are solely responsible for determining the
 appropriateness of using or redistributing the Work and assume any
 risks associated with Your exercise of permissions under this License.

 8. Limitation of Liability. In no event and under no legal theory,
 whether in tort (including negligence), contract, or otherwise,
 unless required by applicable law (such as deliberate and grossly
 negligent acts) or agreed to in writing, shall any Contributor be
 liable to You for damages, including any direct, indirect, special,
 incidental, or consequential damages of any character arising as a
 result of this License or out of the use or inability to use the
 Work (including but not limited to damages for loss of goodwill,
 work stoppage, computer failure or malfunction, or any and all
 other commercial damages or losses), even if such Contributor
 has been advised of the possibility of such damages.

 9. Accepting Warranty or Additional Liability. While redistributing
 the Work or Derivative Works thereof, You may choose to offer,
 and charge a fee for, acceptance of support, warranty, indemnity,
 or other liability obligations and/or rights consistent with this
 License. However, in accepting such obligations, You may act only
 on Your own behalf and on Your sole responsibility, not on behalf
 of any other Contributor, and only if You agree to indemnify,
 defend, and hold each Contributor harmless for any liability
 incurred by, or claims asserted against, such Contributor by reason
 of your accepting any such warranty or additional liability.

 END OF TERMS AND CONDITIONS

 APPENDIX: How to apply the Apache License to your work.

 To apply the Apache License to your work, attach the following
 boilerplate notice, with the fields enclosed by brackets "[]"
 replaced with your own identifying information. (Don't include
 the brackets!)  The text should be enclosed in the appropriate
 comment syntax for the file format. We also recommend that a
 file or class name and description of purpose be included on the
 same "printed page" as the copyright notice for easier
 identification within third-party archives.

 Copyright 2019, Facebook, Inc

 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
 You may obtain a copy of the License at

 http://www.apache.org/licenses/LICENSE-2.0

 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
--- a/MODEL_ZOO.md
+++ b/MODEL_ZOO.md
@@ -0,0 +1,877 @@
 # Detectron2 Model Zoo and Baselines

 ## Introduction

 This file documents a large collection of baselines trained
 with detectron2 in Sep-Oct, 2019.
 The corresponding configurations for all models can be found under the `configs/` directory.
 Unless otherwise noted, the following settings are used for all runs:

 #### Common Settings
 * All models were trained on [Big Basin](https://engineering.fb.com/data-center-engineering/introducing-big-basin-our-next-generation-ai-hardware/)
  servers with 8 NVIDIA V100 GPUs, with data-parallel sync SGD and a total minibatch size of 16 images.
 * All models were trained with CUDA 9.2, cuDNN 7.4.2 or 7.6.3 (the difference in speed is found to be negligible).
 * Training curves and other statistics can be found in `metrics` for each model.
 * The default settings are __not directly comparable__ with Detectron.
  For example, our default training data augmentation uses scale jittering in addition to horizontal flipping.

  For configs that are comparable to Detectron's settings, see
  [Detectron1-Comparisons](configs/Detectron1-Comparisons/) for accuracy comparison,
  and [benchmarks](https://detectron2.readthedocs.io/notes/benchmarks.html)
  for speed comparison.
 * Inference speed is measured by `tools/train_net.py --eval-only`, or [inference_on_dataset()](https://detectron2.readthedocs.io/modules/evaluation.html#detectron2.evaluation.inference_on_dataset),
  with batch size 1 in detectron2 directly.
  The actual deployment should in general be faster than the given inference
  speed due to more optimizations.
 * Training speed is averaged across the entire training.
 	We keep updating the speed with latest version of detectron2/pytorch/etc.,
 	so they might be different from the `metrics` file.
 * All COCO models were trained on `train2017` and evaluated on `val2017`.
 * For Faster/Mask R-CNN, we provide baselines based on __3 different backbone combinations__:
  * __FPN__: Use a ResNet+FPN backbone with standard conv and FC heads for mask and box prediction,
    respectively. It obtains the best
    speed/accuracy tradeoff, but the other two are still useful for research.
  * __C4__: Use a ResNet conv4 backbone with conv5 head. The original baseline in the Faster R-CNN paper.
  * __DC5__ (Dilated-C5): Use a ResNet conv5 backbone with dilations in conv5, and standard conv and FC heads
    for mask and box prediction, respectively.
    This is used by the Deformable ConvNet paper.
 * Most models are trained with the 3x schedule (~37 COCO epochs).
  Although 1x models are heavily under-trained, we provide some ResNet-50 models with the 1x (~12 COCO epochs)
  training schedule for comparison when doing quick research iteration.
 * The *model id* column is provided for ease of reference.
  To check downloaded file integrity, any model on this page contains its md5 prefix in its file name.
 	Each model also comes with a metrics file with all the training statistics and evaluation curves.

 #### ImageNet Pretrained Models

 We provide backbone models pretrained on ImageNet-1k dataset.
 These models are __different__ from those provided in Detectron: we do not fuse BatchNorm into an affine layer.
 * [R-50.pkl](https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl): converted copy of MSRA's original ResNet-50 model
 * [R-101.pkl](https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-101.pkl): converted copy of MSRA's original ResNet-101 model
 * [X-101-32x8d.pkl](https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/FAIR/X-101-32x8d.pkl): ResNeXt-101-32x8d model trained with Caffe2 at FB

 Pretrained models in Detectron's format can still be used. For example:
 * [X-152-32x8d-IN5k.pkl](https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/25093814/X-152-32x8d-IN5k.pkl):
  ResNeXt-152-32x8d model trained on ImageNet-5k with Caffe2 at FB (see ResNeXt paper for details on ImageNet-5k).
 * [R-50-GN.pkl](https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl):
  ResNet-50 with Group Normalization.
 * [R-101-GN.pkl](https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47592356/R-101-GN.pkl):
  ResNet-101 with Group Normalization.

 #### License

 All models available for download through this document are licensed under the
 [Creative Commons Attribution-ShareAlike 3.0 license](https://creativecommons.org/licenses/by-sa/3.0/).

 ### COCO Object Detection Baselines

 #### Faster R-CNN:
 <!--
 (fb only) To update the table in vim:
 1. Remove the old table: d{
 2. Copy the below command to the place of the table
 3. :.!bash

 ./gen_html_table.py --config 'COCO-Detection/faster*50*'{1x,3x}'*' 'COCO-Detection/faster*101*' --name R50-C4 R50-DC5 R50-FPN R50-C4 R50-DC5 R50-FPN R101-C4 R101-DC5 R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: faster_rcnn_R_50_C4_1x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml">R50-C4</a></td>
 <td align="center">1x</td>
 <td align="center">0.551</td>
 <td align="center">0.110</td>
 <td align="center">4.8</td>
 <td align="center">35.7</td>
 <td align="center">137257644</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_1x/137257644/model_final_721ade.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_1x/137257644/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_50_DC5_1x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_DC5_1x.yaml">R50-DC5</a></td>
 <td align="center">1x</td>
 <td align="center">0.380</td>
 <td align="center">0.068</td>
 <td align="center">5.0</td>
 <td align="center">37.3</td>
 <td align="center">137847829</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_1x/137847829/model_final_51d356.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_1x/137847829/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.210</td>
 <td align="center">0.055</td>
 <td align="center">3.0</td>
 <td align="center">37.9</td>
 <td align="center">137257794</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_1x/137257794/model_final_b275ba.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_1x/137257794/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_50_C4_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_C4_3x.yaml">R50-C4</a></td>
 <td align="center">3x</td>
 <td align="center">0.543</td>
 <td align="center">0.110</td>
 <td align="center">4.8</td>
 <td align="center">38.4</td>
 <td align="center">137849393</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_3x/137849393/model_final_f97cb7.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_3x/137849393/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_50_DC5_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml">R50-DC5</a></td>
 <td align="center">3x</td>
 <td align="center">0.378</td>
 <td align="center">0.073</td>
 <td align="center">5.0</td>
 <td align="center">39.0</td>
 <td align="center">137849425</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_3x/137849425/model_final_68d202.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_3x/137849425/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_50_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml">R50-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.209</td>
 <td align="center">0.047</td>
 <td align="center">3.0</td>
 <td align="center">40.2</td>
 <td align="center">137849458</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_101_C4_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_101_C4_3x.yaml">R101-C4</a></td>
 <td align="center">3x</td>
 <td align="center">0.619</td>
 <td align="center">0.149</td>
 <td align="center">5.9</td>
 <td align="center">41.1</td>
 <td align="center">138204752</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_C4_3x/138204752/model_final_298dad.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_C4_3x/138204752/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_101_DC5_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml">R101-DC5</a></td>
 <td align="center">3x</td>
 <td align="center">0.452</td>
 <td align="center">0.082</td>
 <td align="center">6.1</td>
 <td align="center">40.6</td>
 <td align="center">138204841</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_DC5_3x/138204841/model_final_3e0943.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_DC5_3x/138204841/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_101_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml">R101-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.286</td>
 <td align="center">0.063</td>
 <td align="center">4.1</td>
 <td align="center">42.0</td>
 <td align="center">137851257</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_FPN_3x/137851257/model_final_f6e8b1.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_FPN_3x/137851257/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_X_101_32x8d_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml">X101-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.638</td>
 <td align="center">0.120</td>
 <td align="center">6.7</td>
 <td align="center">43.0</td>
 <td align="center">139173657</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x/139173657/model_final_68b088.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x/139173657/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>


 #### RetinaNet:
 <!--
 ./gen_html_table.py --config 'COCO-Detection/retina*50*' 'COCO-Detection/retina*101*' --name R50 R50 R101 --fields lr_sched train_speed inference_speed mem box_AP
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: retinanet_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml">R50</a></td>
 <td align="center">1x</td>
 <td align="center">0.200</td>
 <td align="center">0.062</td>
 <td align="center">3.9</td>
 <td align="center">36.5</td>
 <td align="center">137593951</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_1x/137593951/model_final_b796dc.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_1x/137593951/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: retinanet_R_50_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml">R50</a></td>
 <td align="center">3x</td>
 <td align="center">0.201</td>
 <td align="center">0.063</td>
 <td align="center">3.9</td>
 <td align="center">37.9</td>
 <td align="center">137849486</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_3x/137849486/model_final_4cafe0.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_3x/137849486/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: retinanet_R_101_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Detection/retinanet_R_101_FPN_3x.yaml">R101</a></td>
 <td align="center">3x</td>
 <td align="center">0.280</td>
 <td align="center">0.080</td>
 <td align="center">5.1</td>
 <td align="center">39.9</td>
 <td align="center">138363263</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_101_FPN_3x/138363263/model_final_59f53c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_101_FPN_3x/138363263/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>

 #### RPN & Fast R-CNN:
 <!--
 ./gen_html_table.py --config 'COCO-Detection/rpn*' 'COCO-Detection/fast_rcnn*' --name "RPN R50-C4" "RPN R50-FPN" "Fast R-CNN R50-FPN" --fields lr_sched train_speed inference_speed mem box_AP prop_AR
 -->

 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">prop.<br/>AR</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: rpn_R_50_C4_1x -->
 <tr><td align="left"><a href="configs/COCO-Detection/rpn_R_50_C4_1x.yaml">RPN R50-C4</a></td>
 <td align="center">1x</td>
 <td align="center">0.130</td>
 <td align="center">0.051</td>
 <td align="center">1.5</td>
 <td align="center"></td>
 <td align="center">51.6</td>
 <td align="center">137258005</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_C4_1x/137258005/model_final_450694.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_C4_1x/137258005/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: rpn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/COCO-Detection/rpn_R_50_FPN_1x.yaml">RPN R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.186</td>
 <td align="center">0.045</td>
 <td align="center">2.7</td>
 <td align="center"></td>
 <td align="center">58.0</td>
 <td align="center">137258492</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_FPN_1x/137258492/model_final_02ce48.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_FPN_1x/137258492/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: fast_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml">Fast R-CNN R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.140</td>
 <td align="center">0.035</td>
 <td align="center">2.6</td>
 <td align="center">37.8</td>
 <td align="center"></td>
 <td align="center">137635226</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/model_final_e5f7ce.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>

 ### COCO Instance Segmentation Baselines with Mask R-CNN
 <!--
 ./gen_html_table.py --config 'COCO-InstanceSegmentation/mask*50*'{1x,3x}'*' 'COCO-InstanceSegmentation/mask*101*' --name R50-C4 R50-DC5 R50-FPN R50-C4 R50-DC5 R50-FPN R101-C4 R101-DC5 R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP mask_AP
 -->



 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: mask_rcnn_R_50_C4_1x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml">R50-C4</a></td>
 <td align="center">1x</td>
 <td align="center">0.584</td>
 <td align="center">0.117</td>
 <td align="center">5.2</td>
 <td align="center">36.8</td>
 <td align="center">32.2</td>
 <td align="center">137259246</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x/137259246/model_final_9243eb.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x/137259246/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_DC5_1x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml">R50-DC5</a></td>
 <td align="center">1x</td>
 <td align="center">0.471</td>
 <td align="center">0.074</td>
 <td align="center">6.5</td>
 <td align="center">38.3</td>
 <td align="center">34.2</td>
 <td align="center">137260150</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x/137260150/model_final_4f86c3.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x/137260150/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.261</td>
 <td align="center">0.053</td>
 <td align="center">3.4</td>
 <td align="center">38.6</td>
 <td align="center">35.2</td>
 <td align="center">137260431</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/model_final_a54504.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_C4_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml">R50-C4</a></td>
 <td align="center">3x</td>
 <td align="center">0.575</td>
 <td align="center">0.118</td>
 <td align="center">5.2</td>
 <td align="center">39.8</td>
 <td align="center">34.4</td>
 <td align="center">137849525</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x/137849525/model_final_4ce675.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x/137849525/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_DC5_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml">R50-DC5</a></td>
 <td align="center">3x</td>
 <td align="center">0.470</td>
 <td align="center">0.075</td>
 <td align="center">6.5</td>
 <td align="center">40.0</td>
 <td align="center">35.9</td>
 <td align="center">137849551</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x/137849551/model_final_84107b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x/137849551/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml">R50-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.261</td>
 <td align="center">0.055</td>
 <td align="center">3.4</td>
 <td align="center">41.0</td>
 <td align="center">37.2</td>
 <td align="center">137849600</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_101_C4_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml">R101-C4</a></td>
 <td align="center">3x</td>
 <td align="center">0.652</td>
 <td align="center">0.155</td>
 <td align="center">6.3</td>
 <td align="center">42.6</td>
 <td align="center">36.7</td>
 <td align="center">138363239</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x/138363239/model_final_a2914c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x/138363239/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_101_DC5_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml">R101-DC5</a></td>
 <td align="center">3x</td>
 <td align="center">0.545</td>
 <td align="center">0.155</td>
 <td align="center">7.6</td>
 <td align="center">41.9</td>
 <td align="center">37.3</td>
 <td align="center">138363294</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x/138363294/model_final_0464b7.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x/138363294/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_101_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml">R101-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.340</td>
 <td align="center">0.070</td>
 <td align="center">4.6</td>
 <td align="center">42.9</td>
 <td align="center">38.6</td>
 <td align="center">138205316</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x/138205316/model_final_a3ec72.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x/138205316/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_X_101_32x8d_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml">X101-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.690</td>
 <td align="center">0.129</td>
 <td align="center">7.2</td>
 <td align="center">44.3</td>
 <td align="center">39.5</td>
 <td align="center">139653917</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x/139653917/model_final_2d9806.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x/139653917/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>

 ### COCO Person Keypoint Detection Baselines with Keypoint R-CNN
 <!--
 ./gen_html_table.py --config 'COCO-Keypoints/*50*' 'COCO-Keypoints/*101*'  --name R50-FPN R50-FPN R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP keypoint_AP
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">kp.<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: keypoint_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.315</td>
 <td align="center">0.083</td>
 <td align="center">5.0</td>
 <td align="center">53.6</td>
 <td align="center">64.0</td>
 <td align="center">137261548</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x/137261548/model_final_04e291.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x/137261548/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: keypoint_rcnn_R_50_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml">R50-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.316</td>
 <td align="center">0.076</td>
 <td align="center">5.0</td>
 <td align="center">55.4</td>
 <td align="center">65.5</td>
 <td align="center">137849621</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x/137849621/model_final_a6e10b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x/137849621/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: keypoint_rcnn_R_101_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x.yaml">R101-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.390</td>
 <td align="center">0.090</td>
 <td align="center">6.1</td>
 <td align="center">56.4</td>
 <td align="center">66.1</td>
 <td align="center">138363331</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x/138363331/model_final_997cc7.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x/138363331/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: keypoint_rcnn_X_101_32x8d_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x.yaml">X101-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.738</td>
 <td align="center">0.142</td>
 <td align="center">8.7</td>
 <td align="center">57.3</td>
 <td align="center">66.0</td>
 <td align="center">139686956</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x/139686956/model_final_5ad38f.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x/139686956/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>

 ### COCO Panoptic Segmentation Baselines with Panoptic FPN
 <!--
 ./gen_html_table.py --config 'COCO-PanopticSegmentation/*50*' 'COCO-PanopticSegmentation/*101*'  --name R50-FPN R50-FPN R101-FPN --fields lr_sched train_speed inference_speed mem box_AP mask_AP PQ
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">PQ</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: panoptic_fpn_R_50_1x -->
 <tr><td align="left"><a href="configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml">R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.304</td>
 <td align="center">0.063</td>
 <td align="center">4.8</td>
 <td align="center">37.6</td>
 <td align="center">34.7</td>
 <td align="center">39.4</td>
 <td align="center">139514544</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x/139514544/model_final_dbfeb4.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x/139514544/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: panoptic_fpn_R_50_3x -->
 <tr><td align="left"><a href="configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml">R50-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.302</td>
 <td align="center">0.063</td>
 <td align="center">4.8</td>
 <td align="center">40.0</td>
 <td align="center">36.5</td>
 <td align="center">41.5</td>
 <td align="center">139514569</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x/139514569/model_final_c10459.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x/139514569/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: panoptic_fpn_R_101_3x -->
 <tr><td align="left"><a href="configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml">R101-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.392</td>
 <td align="center">0.078</td>
 <td align="center">6.0</td>
 <td align="center">42.4</td>
 <td align="center">38.5</td>
 <td align="center">43.0</td>
 <td align="center">139514519</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x/139514519/model_final_cafdb1.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x/139514519/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>


 ### LVIS Instance Segmentation Baselines with Mask R-CNN

 Mask R-CNN baselines on the [LVIS dataset](https://lvisdataset.org), v0.5.
 These baselines are described in Table 3(c) of the [LVIS paper](https://arxiv.org/abs/1908.03195).

 NOTE: the 1x schedule here has the same amount of __iterations__ as the COCO 1x baselines.
 They are roughly 24 epochs of LVISv0.5 data.
 The final results of these configs have large variance across different runs.

 <!--
 ./gen_html_table.py --config 'LVIS-InstanceSegmentation/mask*50*' 'LVIS-InstanceSegmentation/mask*101*' --name R50-FPN R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP mask_AP
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: mask_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.292</td>
 <td align="center">0.127</td>
 <td align="center">7.1</td>
 <td align="center">23.6</td>
 <td align="center">24.4</td>
 <td align="center">144219072</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/144219072/model_final_571f7c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/144219072/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_101_FPN_1x -->
 <tr><td align="left"><a href="configs/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x.yaml">R101-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.371</td>
 <td align="center">0.124</td>
 <td align="center">7.8</td>
 <td align="center">25.6</td>
 <td align="center">25.9</td>
 <td align="center">144219035</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x/144219035/model_final_824ab5.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x/144219035/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_X_101_32x8d_FPN_1x -->
 <tr><td align="left"><a href="configs/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x.yaml">X101-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.712</td>
 <td align="center">0.166</td>
 <td align="center">10.2</td>
 <td align="center">26.7</td>
 <td align="center">27.1</td>
 <td align="center">144219108</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x/144219108/model_final_5e3439.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x/144219108/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>



 ### Cityscapes & Pascal VOC Baselines

 Simple baselines for
 * Mask R-CNN on Cityscapes instance segmentation (initialized from COCO pre-training, then trained on Cityscapes fine annotations only)
 * Faster R-CNN on PASCAL VOC object detection (trained on VOC 2007 train+val + VOC 2012 train+val, tested on VOC 2007 using 11-point interpolated AP)

 <!--
 ./gen_html_table.py --config 'Cityscapes/*' 'PascalVOC-Detection/*' --name "R50-FPN, Cityscapes" "R50-C4, VOC" --fields train_speed inference_speed mem box_AP box_AP50 mask_AP
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">box<br/>AP50</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: mask_rcnn_R_50_FPN -->
 <tr><td align="left"><a href="configs/Cityscapes/mask_rcnn_R_50_FPN.yaml">R50-FPN, Cityscapes</a></td>
 <td align="center">0.240</td>
 <td align="center">0.092</td>
 <td align="center">4.4</td>
 <td align="center"></td>
 <td align="center"></td>
 <td align="center">36.5</td>
 <td align="center">142423278</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Cityscapes/mask_rcnn_R_50_FPN/142423278/model_final_af9cf5.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Cityscapes/mask_rcnn_R_50_FPN/142423278/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: faster_rcnn_R_50_C4 -->
 <tr><td align="left"><a href="configs/PascalVOC-Detection/faster_rcnn_R_50_C4.yaml">R50-C4, VOC</a></td>
 <td align="center">0.537</td>
 <td align="center">0.086</td>
 <td align="center">4.8</td>
 <td align="center">51.9</td>
 <td align="center">80.3</td>
 <td align="center"></td>
 <td align="center">142202221</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/PascalVOC-Detection/faster_rcnn_R_50_C4/142202221/model_final_b1acc2.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/PascalVOC-Detection/faster_rcnn_R_50_C4/142202221/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>



 ### Other Settings

 Ablations for Deformable Conv and Cascade R-CNN:

 <!--
 ./gen_html_table.py --config 'COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml' 'Misc/*R_50_FPN_1x_dconv*' 'Misc/cascade*1x.yaml' 'COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml' 'Misc/*R_50_FPN_3x_dconv*' 'Misc/cascade*3x.yaml' --name "Baseline R50-FPN" "Deformable Conv" "Cascade R-CNN" "Baseline R50-FPN" "Deformable Conv" "Cascade R-CNN"  --fields lr_sched train_speed inference_speed mem box_AP mask_AP
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: mask_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml">Baseline R50-FPN</a></td>
 <td align="center">1x</td>
 <td align="center">0.261</td>
 <td align="center">0.053</td>
 <td align="center">3.4</td>
 <td align="center">38.6</td>
 <td align="center">35.2</td>
 <td align="center">137260431</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/model_final_a54504.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_1x_dconv_c3-c5 -->
 <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml">Deformable Conv</a></td>
 <td align="center">1x</td>
 <td align="center">0.342</td>
 <td align="center">0.061</td>
 <td align="center">3.5</td>
 <td align="center">41.5</td>
 <td align="center">37.5</td>
 <td align="center">138602867</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5/138602867/model_final_65c703.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5/138602867/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: cascade_mask_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/Misc/cascade_mask_rcnn_R_50_FPN_1x.yaml">Cascade R-CNN</a></td>
 <td align="center">1x</td>
 <td align="center">0.317</td>
 <td align="center">0.066</td>
 <td align="center">4.0</td>
 <td align="center">42.1</td>
 <td align="center">36.4</td>
 <td align="center">138602847</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_1x/138602847/model_final_e9d89b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_1x/138602847/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml">Baseline R50-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.261</td>
 <td align="center">0.055</td>
 <td align="center">3.4</td>
 <td align="center">41.0</td>
 <td align="center">37.2</td>
 <td align="center">137849600</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_3x_dconv_c3-c5 -->
 <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml">Deformable Conv</a></td>
 <td align="center">3x</td>
 <td align="center">0.349</td>
 <td align="center">0.066</td>
 <td align="center">3.5</td>
 <td align="center">42.7</td>
 <td align="center">38.5</td>
 <td align="center">144998336</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5/144998336/model_final_821d0b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5/144998336/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: cascade_mask_rcnn_R_50_FPN_3x -->
 <tr><td align="left"><a href="configs/Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml">Cascade R-CNN</a></td>
 <td align="center">3x</td>
 <td align="center">0.328</td>
 <td align="center">0.075</td>
 <td align="center">4.0</td>
 <td align="center">44.3</td>
 <td align="center">38.5</td>
 <td align="center">144998488</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>


 Ablations for normalization methods:
 (Note: The baseline uses `2fc` head while the others use `4conv1fc` head. According to the
 [GroupNorm paper](https://arxiv.org/abs/1803.08494), the change in head does not improve the baseline by much)
 <!--
 ./gen_html_table.py --config 'COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml' 'Misc/mask*50_FPN_3x_syncbn.yaml' 'Misc/mask*50_FPN_3x_gn.yaml' 'Misc/scratch*' --name "Baseline R50-FPN" "SyncBN" "GN" "GN (scratch)" --fields lr_sched train_speed inference_speed mem box_AP mask_AP
   -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: mask_rcnn_R_50_FPN_3x -->
 <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml">Baseline R50-FPN</a></td>
 <td align="center">3x</td>
 <td align="center">0.261</td>
 <td align="center">0.055</td>
 <td align="center">3.4</td>
 <td align="center">41.0</td>
 <td align="center">37.2</td>
 <td align="center">137849600</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_3x_syncbn -->
 <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_3x_syncbn.yaml">SyncBN</a></td>
 <td align="center">3x</td>
 <td align="center">0.464</td>
 <td align="center">0.063</td>
 <td align="center">5.6</td>
 <td align="center">42.0</td>
 <td align="center">37.8</td>
 <td align="center">143915318</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_syncbn/143915318/model_final_220cfb.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_syncbn/143915318/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_3x_gn -->
 <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_3x_gn.yaml">GN</a></td>
 <td align="center">3x</td>
 <td align="center">0.356</td>
 <td align="center">0.077</td>
 <td align="center">7.3</td>
 <td align="center">42.6</td>
 <td align="center">38.6</td>
 <td align="center">138602888</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_gn/138602888/model_final_dc5d9e.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_gn/138602888/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: scratch_mask_rcnn_R_50_FPN_3x_gn -->
 <tr><td align="left"><a href="configs/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn.yaml">GN (scratch)</a></td>
 <td align="center">3x</td>
 <td align="center">0.400</td>
 <td align="center">0.077</td>
 <td align="center">9.8</td>
 <td align="center">39.9</td>
 <td align="center">36.6</td>
 <td align="center">138602908</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn/138602908/model_final_01ca85.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn/138602908/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>



 A few very large models trained for a long time, for demo purposes:

 <!--
 ./gen_html_table.py --config 'Misc/panoptic_*dconv*' 'Misc/cascade_*152*' --name "Panoptic FPN R101" "Mask R-CNN X152" --fields inference_speed mem box_AP mask_AP PQ
 # manually add TTA results
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">PQ</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: panoptic_fpn_R_101_dconv_cascade_gn_3x -->
 <tr><td align="left"><a href="configs/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml">Panoptic FPN R101</a></td>
 <td align="center">0.123</td>
 <td align="center">11.4</td>
 <td align="center">47.4</td>
 <td align="center">41.3</td>
 <td align="center">46.1</td>
 <td align="center">139797668</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x/139797668/model_final_be35db.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x/139797668/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv -->
 <tr><td align="left"><a href="configs/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml">Mask R-CNN X152</a></td>
 <td align="center">0.281</td>
 <td align="center">15.1</td>
 <td align="center">50.2</td>
 <td align="center">44.0</td>
 <td align="center"></td>
 <td align="center">18131413</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv/18131413/model_0039999_e76410.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv/18131413/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: TTA cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv -->
 <tr><td align="left">above + test-time aug.</td>
 <td align="center"></td>
 <td align="center"></td>
 <td align="center">51.9</td>
 <td align="center">45.9</td>
 <td align="center"></td>
 <td align="center"></td>
 <td align="center"></td>
 </tr>
 </tbody></table>
--- a/README.md
+++ b/README.md
@@ -1,2 +1,104 @@
 # detectron
 ### Requirements
 - Python >= 3.6(Conda)
 - PyTorch 1.3
 - [torchvision](https://github.com/pytorch/vision/) that matches the PyTorch installation.
 	You can install them together at [pytorch.org](https://pytorch.org) to make sure of this.
 - OpenCV, needed by demo and visualization
 - [fvcore](https://github.com/facebookresearch/fvcore/): `pip install git+https://github.com/facebookresearch/fvcore`
 - pycocotools: `pip install cython; pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI`
 - VS2019(no test in older version)/CUDA10.1(no test in older version)

 ### several files must be changed by manually.
 ```
 file1: 
  {your evn path}\Lib\site-packages\torch\include\torch\csrc\jit\argument_spec.h
  example:
  {C:\Miniconda3\envs\py36}\Lib\site-packages\torch\include\torch\csrc\jit\argument_spec.h(190)
    static constexpr size_t DEPTH_LIMIT = 128;
      change to -->
    static const size_t DEPTH_LIMIT = 128;
 file2: 
  {your evn path}\Lib\site-packages\torch\include\pybind11\cast.h
  example:
  {C:\Miniconda3\envs\py36}\Lib\site-packages\torch\include\pybind11\cast.h(1449)
    explicit operator type&() { return *(this->value); }
      change to -->
    explicit operator type&() { return *((type*)this->value); }
 ```

 ### Build detectron2

 After having the above dependencies, run:
 ```
 conda activate {your env}

 "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat"

 git clone https://github.com/conansherry/detectron2

 cd detectron2

 python setup.py build develop
 ```
 Note: you may need to rebuild detectron2 after reinstalling a different build of PyTorch.

 <div align="center">
  <img src="docs/windows_build.png"/>
 </div>

 <img src=".github/Detectron2-Logo-Horz.svg" width="300" >

 Detectron2 is Facebook AI Research's next generation software system
 that implements state-of-the-art object detection algorithms.
 It is a ground-up rewrite of the previous version,
 [Detectron](https://github.com/facebookresearch/Detectron/),
 and it originates from [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark/).

 <div align="center">
  <img src="https://user-images.githubusercontent.com/1381301/66535560-d3422200-eace-11e9-9123-5535d469db19.png"/>
 </div>

 ### What's New
 * It is powered by the [PyTorch](https://pytorch.org) deep learning framework.
 * Includes more features such as panoptic segmentation, densepose, Cascade R-CNN, rotated bounding boxes, etc.
 * Can be used as a library to support [different projects](projects/) on top of it.
  We'll open source more research projects in this way.
 * It [trains much faster](https://detectron2.readthedocs.io/notes/benchmarks.html).

 See our [blog post](https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/)
 to see more demos and learn about detectron2.

 ## Installation

 See [INSTALL.md](INSTALL.md).

 ## Quick Start

 See [GETTING_STARTED.md](GETTING_STARTED.md),
 or the [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5).

 Learn more at our [documentation](https://detectron2.readthedocs.org).
 And see [projects/](projects/) for some projects that are built on top of detectron2.

 ## Model Zoo and Baselines

 We provide a large set of baseline results and trained models available for download in the [Detectron2 Model Zoo](MODEL_ZOO.md).


 ## License

 Detectron2 is released under the [Apache 2.0 license](LICENSE).

 ## Citing Detectron

 If you use Detectron2 in your research or wish to refer to the baseline results published in the [Model Zoo](MODEL_ZOO.md), please use the following BibTeX entry.

 ```BibTeX
@misc{wu2019detectron2,
  author =       {Yuxin Wu and Alexander Kirillov and Francisco Massa and
                  Wan-Yen Lo and Ross Girshick},
  title =        {Detectron2},
  howpublished = {\url{https://github.com/facebookresearch/detectron2}},
  year =         {2019}
 }
 ```
--- a/configs/Base-RCNN-C4.yaml
+++ b/configs/Base-RCNN-C4.yaml
@@ -0,0 +1,18 @@
 MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  RPN:
    PRE_NMS_TOPK_TEST: 6000
    POST_NMS_TOPK_TEST: 1000
  ROI_HEADS:
    NAME: "Res5ROIHeads"
 DATASETS:
  TRAIN: ("coco_2017_train",)
  TEST: ("coco_2017_val",)
 SOLVER:
  IMS_PER_BATCH: 16
  BASE_LR: 0.02
  STEPS: (60000, 80000)
  MAX_ITER: 90000
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)

--- a/configs/Base-RCNN-DilatedC5.yaml
+++ b/configs/Base-RCNN-DilatedC5.yaml
@@ -0,0 +1,30 @@
 MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  RESNETS:
    OUT_FEATURES: ["res5"]
    RES5_DILATION: 2
  RPN:
    IN_FEATURES: ["res5"]
    PRE_NMS_TOPK_TEST: 6000
    POST_NMS_TOPK_TEST: 1000
  ROI_HEADS:
    NAME: "StandardROIHeads"
    IN_FEATURES: ["res5"]
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_FC: 2
    POOLER_RESOLUTION: 7
  ROI_MASK_HEAD:
    NAME: "MaskRCNNConvUpsampleHead"
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
 DATASETS:
  TRAIN: ("coco_2017_train",)
  TEST: ("coco_2017_val",)
 SOLVER:
  IMS_PER_BATCH: 16
  BASE_LR: 0.02
  STEPS: (60000, 80000)
  MAX_ITER: 90000
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
--- a/configs/Base-RCNN-FPN.yaml
+++ b/configs/Base-RCNN-FPN.yaml
@@ -0,0 +1,41 @@
 MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  BACKBONE:
    NAME: "build_resnet_fpn_backbone"
  RESNETS:
    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
  FPN:
    IN_FEATURES: ["res2", "res3", "res4", "res5"]
  ANCHOR_GENERATOR:
    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
  RPN:
    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
    # Detectron1 uses 2000 proposals per-batch,
    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
    POST_NMS_TOPK_TRAIN: 1000
    POST_NMS_TOPK_TEST: 1000
  ROI_HEADS:
    NAME: "StandardROIHeads"
    IN_FEATURES: ["p2", "p3", "p4", "p5"]
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_FC: 2
    POOLER_RESOLUTION: 7
  ROI_MASK_HEAD:
    NAME: "MaskRCNNConvUpsampleHead"
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
 DATASETS:
  TRAIN: ("coco_2017_train",)
  TEST: ("coco_2017_val",)
 SOLVER:
  IMS_PER_BATCH: 16
  BASE_LR: 0.02
  STEPS: (60000, 80000)
  MAX_ITER: 90000
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
--- a/configs/Base-RetinaNet.yaml
+++ b/configs/Base-RetinaNet.yaml
@@ -0,0 +1,23 @@
 MODEL:
  META_ARCHITECTURE: "RetinaNet"
  BACKBONE:
    NAME: "build_retinanet_resnet_fpn_backbone"
  RESNETS:
    OUT_FEATURES: ["res3", "res4", "res5"]
  ANCHOR_GENERATOR:
    SIZES: !!python/object/apply:eval ["[[x, x * 2**(1.0/3), x * 2**(2.0/3) ] for x in [32, 64, 128, 256, 512 ]]"]
  FPN:
    IN_FEATURES: ["res3", "res4", "res5"]
  RETINANET:
    IOU_THRESHOLDS: [0.4, 0.5]
    IOU_LABELS: [0, -1, 1]
 DATASETS:
  TRAIN: ("coco_2017_train",)
  TEST: ("coco_2017_val",)
 SOLVER:
  IMS_PER_BATCH: 16
  BASE_LR: 0.01  # Note that RetinaNet uses a different default learning rate
  STEPS: (60000, 80000)
  MAX_ITER: 90000
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
--- a/configs/COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml
+++ b/configs/COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml
@@ -0,0 +1,17 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  LOAD_PROPOSALS: True
  RESNETS:
    DEPTH: 50
  PROPOSAL_GENERATOR:
    NAME: "PrecomputedProposals"
 DATASETS:
  TRAIN: ("coco_2017_train",)
  PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_train_box_proposals_21bc3a.pkl", )
  TEST: ("coco_2017_val",)
  PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
 DATALOADER:
  # proposals are part of the dataset_dicts, and take a lot of RAM
  NUM_WORKERS: 2
--- a/configs/COCO-Detection/faster_rcnn_R_101_C4_3x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_101_C4_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-DilatedC5.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml
@@ -0,0 +1,6 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-Detection/faster_rcnn_R_50_C4_3x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_50_C4_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/faster_rcnn_R_50_DC5_1x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_50_DC5_1x.yaml
@@ -0,0 +1,6 @@
 _BASE_: "../Base-RCNN-DilatedC5.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-DilatedC5.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml
@@ -0,0 +1,6 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml
+++ b/configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml
@@ -0,0 +1,13 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  MASK_ON: False
  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
  PIXEL_STD: [57.375, 57.120, 58.395]
  RESNETS:
    STRIDE_IN_1X1: False  # this is a C2 model
    NUM_GROUPS: 32
    WIDTH_PER_GROUP: 8
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/retinanet_R_101_FPN_3x.yaml
+++ b/configs/COCO-Detection/retinanet_R_101_FPN_3x.yaml
@@ -0,0 +1,8 @@
 _BASE_: "../Base-RetinaNet.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml
+++ b/configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml
@@ -0,0 +1,5 @@
 _BASE_: "../Base-RetinaNet.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml
+++ b/configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml
@@ -0,0 +1,8 @@
 _BASE_: "../Base-RetinaNet.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Detection/rpn_R_50_C4_1x.yaml
+++ b/configs/COCO-Detection/rpn_R_50_C4_1x.yaml
@@ -0,0 +1,10 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  META_ARCHITECTURE: "ProposalNetwork"
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
  RPN:
    PRE_NMS_TOPK_TEST: 12000
    POST_NMS_TOPK_TEST: 2000
--- a/configs/COCO-Detection/rpn_R_50_FPN_1x.yaml
+++ b/configs/COCO-Detection/rpn_R_50_FPN_1x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "ProposalNetwork"
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
  RPN:
    POST_NMS_TOPK_TEST: 2000
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-DilatedC5.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml
@@ -0,0 +1,6 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml
@@ -0,0 +1,6 @@
 _BASE_: "../Base-RCNN-DilatedC5.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-DilatedC5.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml
@@ -0,0 +1,6 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml
+++ b/configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml
@@ -0,0 +1,13 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  MASK_ON: True
  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
  PIXEL_STD: [57.375, 57.120, 58.395]
  RESNETS:
    STRIDE_IN_1X1: False  # this is a C2 model
    NUM_GROUPS: 32
    WIDTH_PER_GROUP: 8
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Keypoints/Base-Keypoint-RCNN-FPN.yaml
+++ b/configs/COCO-Keypoints/Base-Keypoint-RCNN-FPN.yaml
@@ -0,0 +1,15 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  KEYPOINT_ON: True
  ROI_HEADS:
    NUM_CLASSES: 1
  ROI_BOX_HEAD:
    SMOOTH_L1_BETA: 0.5  # Keypoint AP degrades (though box AP improves) when using plain L1 loss
  RPN:
    # Detectron1 uses 2000 proposals per-batch, but this option is per-image in detectron2.
    # 1000 proposals per-image is found to hurt box AP.
    # Therefore we increase it to 1500 per-image.
    POST_NMS_TOPK_TRAIN: 1500
 DATASETS:
  TRAIN: ("keypoints_coco_2017_train",)
  TEST: ("keypoints_coco_2017_val",)
--- a/configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x.yaml
+++ b/configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x.yaml
@@ -0,0 +1,8 @@
 _BASE_: "Base-Keypoint-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml
+++ b/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml
@@ -0,0 +1,5 @@
 _BASE_: "Base-Keypoint-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml
+++ b/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml
@@ -0,0 +1,8 @@
 _BASE_: "Base-Keypoint-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x.yaml
+++ b/configs/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x.yaml
@@ -0,0 +1,12 @@
 _BASE_: "Base-Keypoint-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
  PIXEL_STD: [57.375, 57.120, 58.395]
  RESNETS:
    STRIDE_IN_1X1: False  # this is a C2 model
    NUM_GROUPS: 32
    WIDTH_PER_GROUP: 8
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml
+++ b/configs/COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml
@@ -0,0 +1,9 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "PanopticFPN"
  MASK_ON: True
  SEM_SEG_HEAD:
    LOSS_WEIGHT: 0.5
 DATASETS:
  TRAIN: ("coco_2017_train_panoptic_separated",)
  TEST: ("coco_2017_val_panoptic_separated",)
--- a/configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml
+++ b/configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml
@@ -0,0 +1,8 @@
 _BASE_: "Base-Panoptic-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  RESNETS:
    DEPTH: 101
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml
+++ b/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml
@@ -0,0 +1,5 @@
 _BASE_: "Base-Panoptic-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
--- a/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml
+++ b/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml
@@ -0,0 +1,8 @@
 _BASE_: "Base-Panoptic-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/Cityscapes/mask_rcnn_R_50_FPN.yaml
+++ b/configs/Cityscapes/mask_rcnn_R_50_FPN.yaml
@@ -0,0 +1,25 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  # WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  # For better, more stable performance initialize from COCO
  WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"
  MASK_ON: True
  ROI_HEADS:
    NUM_CLASSES: 8
 # This is the setting used in Mask R-CNN paper, Appendix A
 INPUT:
  MIN_SIZE_TRAIN: (800, 832, 864, 896, 928, 960, 992, 1024)
  MIN_SIZE_TRAIN_SAMPLING: "choice"
  MIN_SIZE_TEST: 1024
  MAX_SIZE_TRAIN: 2048
  MAX_SIZE_TEST: 2048
 DATASETS:
  TRAIN: ("cityscapes_fine_instance_seg_train",)
  TEST: ("cityscapes_fine_instance_seg_val",)
 SOLVER:
  BASE_LR: 0.01
  STEPS: (18000,)
  MAX_ITER: 24000
  IMS_PER_BATCH: 8
 TEST:
  EVAL_PERIOD: 8000
--- a/configs/Detectron1-Comparisons/README.md
+++ b/configs/Detectron1-Comparisons/README.md
@@ -0,0 +1,81 @@

 Detectron2's default settings and a few implementation details are different from Detectron.

 The differences in implementation details are shared in
 [Compatibility with Other Libraries](../../docs/notes/compatibility.md).

 The differences in default config includes:
 * Use scale augmentation during training.
 * Use L1 loss instead of smooth L1 loss.
 * Use `POOLER_SAMPLING_RATIO=0` instead of 2.
 * Use `ROIAlignV2`.

 In this directory, we provide a few configs that mimic Detectron's behavior as close as possible.
 This provides a fair comparison of accuracy and speed against Detectron.

 <!--
 ./gen_html_table.py --config 'Detectron1-Comparisons/*.yaml' --name "Faster R-CNN" "Keypoint R-CNN" "Mask R-CNN" --fields lr_sched train_speed inference_speed mem box_AP mask_AP keypoint_AP
 -->


 <table><tbody>
 <!-- START TABLE -->
 <!-- TABLE HEADER -->
 <th valign="bottom">Name</th>
 <th valign="bottom">lr<br/>sched</th>
 <th valign="bottom">train<br/>time<br/>(s/iter)</th>
 <th valign="bottom">inference<br/>time<br/>(s/im)</th>
 <th valign="bottom">train<br/>mem<br/>(GB)</th>
 <th valign="bottom">box<br/>AP</th>
 <th valign="bottom">mask<br/>AP</th>
 <th valign="bottom">kp.<br/>AP</th>
 <th valign="bottom">model id</th>
 <th valign="bottom">download</th>
 <!-- TABLE BODY -->
 <!-- ROW: faster_rcnn_R_50_FPN_noaug_1x -->
 <tr><td align="left"><a href="configs/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x.yaml">Faster R-CNN</a></td>
 <td align="center">1x</td>
 <td align="center">0.219</td>
 <td align="center">0.048</td>
 <td align="center">3.1</td>
 <td align="center">36.9</td>
 <td align="center"></td>
 <td align="center"></td>
 <td align="center">137781054</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x/137781054/model_final_7ab50c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x/137781054/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: keypoint_rcnn_R_50_FPN_1x -->
 <tr><td align="left"><a href="configs/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x.yaml">Keypoint R-CNN</a></td>
 <td align="center">1x</td>
 <td align="center">0.313</td>
 <td align="center">0.082</td>
 <td align="center">5.0</td>
 <td align="center">53.1</td>
 <td align="center"></td>
 <td align="center">64.2</td>
 <td align="center">137781195</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x/137781195/model_final_cce136.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x/137781195/metrics.json">metrics</a></td>
 </tr>
 <!-- ROW: mask_rcnn_R_50_FPN_noaug_1x -->
 <tr><td align="left"><a href="configs/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x.yaml">Mask R-CNN</a></td>
 <td align="center">1x</td>
 <td align="center">0.273</td>
 <td align="center">0.052</td>
 <td align="center">3.4</td>
 <td align="center">37.8</td>
 <td align="center">34.9</td>
 <td align="center"></td>
 <td align="center">137781281</td>
 <td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x/137781281/model_final_62ca52.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x/137781281/metrics.json">metrics</a></td>
 </tr>
 </tbody></table>

 ## Comparisons:

 * Faster R-CNN: Detectron's AP is 36.7, similar to ours.
 * Keypoint R-CNN: Detectron's AP is box 53.6, keypoint 64.2. Fixing a Detectron's
  [bug](https://github.com/facebookresearch/Detectron/issues/459) lead to a drop in box AP, and can be
 	compensated back by some parameter tuning.
 * Mask R-CNN: Detectron's AP is box 37.7, mask 33.9. We're 1 AP better in mask AP, due to more correct implementation.

 For speed comparison, see [benchmarks](https://detectron2.readthedocs.io/notes/benchmarks.html).
--- a/configs/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x.yaml
+++ b/configs/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x.yaml
@@ -0,0 +1,17 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
  # Detectron1 uses smooth L1 loss with some magic beta values.
  # The defaults are changed to L1 loss in Detectron2.
  RPN:
    SMOOTH_L1_BETA: 0.1111
  ROI_BOX_HEAD:
    SMOOTH_L1_BETA: 1.0
    POOLER_SAMPLING_RATIO: 2
    POOLER_TYPE: "ROIAlign"
 INPUT:
  # no scale augmentation
  MIN_SIZE_TRAIN: (800, )
--- a/configs/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x.yaml
+++ b/configs/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x.yaml
@@ -0,0 +1,27 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  KEYPOINT_ON: True
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    NUM_CLASSES: 1
  ROI_KEYPOINT_HEAD:
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 2
    POOLER_TYPE: "ROIAlign"
  # Detectron1 uses smooth L1 loss with some magic beta values.
  # The defaults are changed to L1 loss in Detectron2.
  ROI_BOX_HEAD:
    SMOOTH_L1_BETA: 1.0
    POOLER_SAMPLING_RATIO: 2
    POOLER_TYPE: "ROIAlign"
  RPN:
    SMOOTH_L1_BETA: 0.1111
    # Detectron1 uses 2000 proposals per-batch, but this option is per-image in detectron2
    # 1000 proposals per-image is found to hurt box AP.
    # Therefore we increase it to 1500 per-image.
    POST_NMS_TOPK_TRAIN: 1500
 DATASETS:
  TRAIN: ("keypoints_coco_2017_train",)
  TEST: ("keypoints_coco_2017_val",)
--- a/configs/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x.yaml
+++ b/configs/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x.yaml
@@ -0,0 +1,20 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
  # Detectron1 uses smooth L1 loss with some magic beta values.
  # The defaults are changed to L1 loss in Detectron2.
  RPN:
    SMOOTH_L1_BETA: 0.1111
  ROI_BOX_HEAD:
    SMOOTH_L1_BETA: 1.0
    POOLER_SAMPLING_RATIO: 2
    POOLER_TYPE: "ROIAlign"
  ROI_MASK_HEAD:
    POOLER_SAMPLING_RATIO: 2
    POOLER_TYPE: "ROIAlign"
 INPUT:
  # no scale augmentation
  MIN_SIZE_TRAIN: (800, )
--- a/configs/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x.yaml
+++ b/configs/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x.yaml
@@ -0,0 +1,19 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 101
  ROI_HEADS:
    NUM_CLASSES: 1230
    SCORE_THRESH_TEST: 0.0001
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
 DATASETS:
  TRAIN: ("lvis_v0.5_train",)
  TEST: ("lvis_v0.5_val",)
 TEST:
  DETECTIONS_PER_IMAGE: 300  # LVIS allows up to 300
 DATALOADER:
  SAMPLER_TRAIN: "RepeatFactorTrainingSampler"
  REPEAT_THRESHOLD: 0.001
--- a/configs/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml
+++ b/configs/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml
@@ -0,0 +1,19 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    NUM_CLASSES: 1230
    SCORE_THRESH_TEST: 0.0001
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
 DATASETS:
  TRAIN: ("lvis_v0.5_train",)
  TEST: ("lvis_v0.5_val",)
 TEST:
  DETECTIONS_PER_IMAGE: 300  # LVIS allows up to 300
 DATALOADER:
  SAMPLER_TRAIN: "RepeatFactorTrainingSampler"
  REPEAT_THRESHOLD: 0.001
--- a/configs/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x.yaml
+++ b/configs/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x.yaml
@@ -0,0 +1,23 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
  PIXEL_STD: [57.375, 57.120, 58.395]
  MASK_ON: True
  RESNETS:
    STRIDE_IN_1X1: False  # this is a C2 model
    NUM_GROUPS: 32
    WIDTH_PER_GROUP: 8
    DEPTH: 101
  ROI_HEADS:
    NUM_CLASSES: 1230
    SCORE_THRESH_TEST: 0.0001
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
 DATASETS:
  TRAIN: ("lvis_v0.5_train",)
  TEST: ("lvis_v0.5_val",)
 TEST:
  DETECTIONS_PER_IMAGE: 300  # LVIS allows up to 300
 DATALOADER:
  SAMPLER_TRAIN: "RepeatFactorTrainingSampler"
  REPEAT_THRESHOLD: 0.001
--- a/configs/Misc/cascade_mask_rcnn_R_50_FPN_1x.yaml
+++ b/configs/Misc/cascade_mask_rcnn_R_50_FPN_1x.yaml
@@ -0,0 +1,12 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    NAME: CascadeROIHeads
  ROI_BOX_HEAD:
    CLS_AGNOSTIC_BBOX_REG: True
  RPN:
    POST_NMS_TOPK_TRAIN: 2000
--- a/configs/Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml
+++ b/configs/Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml
@@ -0,0 +1,15 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    NAME: CascadeROIHeads
  ROI_BOX_HEAD:
    CLS_AGNOSTIC_BBOX_REG: True
  RPN:
    POST_NMS_TOPK_TRAIN: 2000
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml
+++ b/configs/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml
@@ -0,0 +1,36 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  MASK_ON: True
  WEIGHTS: "catalog://ImageNetPretrained/FAIR/X-152-32x8d-IN5k"
  RESNETS:
    STRIDE_IN_1X1: False  # this is a C2 model
    NUM_GROUPS: 32
    WIDTH_PER_GROUP: 8
    DEPTH: 152
    DEFORM_ON_PER_STAGE: [False, True, True, True]
  ROI_HEADS:
    NAME: "CascadeROIHeads"
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_CONV: 4
    NUM_FC: 1
    NORM: "GN"
    CLS_AGNOSTIC_BBOX_REG: True
  ROI_MASK_HEAD:
    NUM_CONV: 8
    NORM: "GN"
  RPN:
    POST_NMS_TOPK_TRAIN: 2000
 SOLVER:
  IMS_PER_BATCH: 128
  STEPS: (35000, 45000)
  MAX_ITER: 50000
  BASE_LR: 0.16
 INPUT:
  MIN_SIZE_TRAIN: (640, 864)
  MIN_SIZE_TRAIN_SAMPLING: "range"
  MAX_SIZE_TRAIN: 1440
  CROP:
    ENABLED: True
 TEST:
  EVAL_PERIOD: 2500
--- a/configs/Misc/mask_rcnn_R_50_FPN_1x_cls_agnostic.yaml
+++ b/configs/Misc/mask_rcnn_R_50_FPN_1x_cls_agnostic.yaml
@@ -0,0 +1,10 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
  ROI_BOX_HEAD:
    CLS_AGNOSTIC_BBOX_REG: True
  ROI_MASK_HEAD:
    CLS_AGNOSTIC_MASK: True
--- a/configs/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml
+++ b/configs/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml
@@ -0,0 +1,8 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
    DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5
    DEFORM_MODULATED: False
--- a/configs/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml
+++ b/configs/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml
@@ -0,0 +1,11 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
    DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5
    DEFORM_MODULATED: False
 SOLVER:
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/Misc/mask_rcnn_R_50_FPN_3x_gn.yaml
+++ b/configs/Misc/mask_rcnn_R_50_FPN_3x_gn.yaml
@@ -0,0 +1,21 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-50-GN"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
    NORM: "GN"
    STRIDE_IN_1X1: False
  FPN:
    NORM: "GN"
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_CONV: 4
    NUM_FC: 1
    NORM: "GN"
  ROI_MASK_HEAD:
    NORM: "GN"
 SOLVER:
  # 3x schedule
  STEPS: (210000, 250000)
  MAX_ITER: 270000
--- a/configs/Misc/mask_rcnn_R_50_FPN_3x_syncbn.yaml
+++ b/configs/Misc/mask_rcnn_R_50_FPN_3x_syncbn.yaml
@@ -0,0 +1,24 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
    NORM: "SyncBN"
    STRIDE_IN_1X1: False
  FPN:
    NORM: "SyncBN"
  ROI_BOX_HEAD:
    NAME: "FastRCNNConvFCHead"
    NUM_CONV: 4
    NUM_FC: 1
    NORM: "SyncBN"
  ROI_MASK_HEAD:
    NORM: "SyncBN"
 SOLVER:
  # 3x schedule
  STEPS: (210000, 250000)
  MAX_ITER: 270000
 TEST:
  PRECISE_BN:
    ENABLED: True
--- a/configs/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml
+++ b/configs/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml
@@ -0,0 +1,26 @@
 # A large PanopticFPN for demo purposes.
 # Use GN on backbone to support semantic seg.
 # Use Cascade + Deform Conv to improve localization.
 _BASE_: "../COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml"
 MODEL:
  WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-101-GN"
  RESNETS:
    DEPTH: 101
    NORM: "GN"
    DEFORM_ON_PER_STAGE: [False, True, True, True]
    STRIDE_IN_1X1: False
  FPN:
    NORM: "GN"
  ROI_HEADS:
    NAME: CascadeROIHeads
  ROI_BOX_HEAD:
    CLS_AGNOSTIC_BBOX_REG: True
  ROI_MASK_HEAD:
    NORM: "GN"
  RPN:
    POST_NMS_TOPK_TRAIN: 2000
 SOLVER:
  STEPS: (105000, 125000)
  MAX_ITER: 135000
  IMS_PER_BATCH: 32
  BASE_LR: 0.04
--- a/configs/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn.yaml
+++ b/configs/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn.yaml
@@ -0,0 +1,11 @@
 _BASE_: "mask_rcnn_R_50_FPN_3x_gn.yaml"
 # INPUT:
  # It makes sense to divide by STD when training from scratch
  # But it seems to make no difference on the results and C2's models didn't do this.
  # So we keep things consistent with C2.
  # PIXEL_STD: [57.375, 57.12, 58.395]
 MODEL:
  WEIGHTS: ""
  MASK_ON: True
  BACKBONE:
    FREEZE_AT: 0
--- a/configs/Misc/semantic_R_50_FPN_1x.yaml
+++ b/configs/Misc/semantic_R_50_FPN_1x.yaml
@@ -0,0 +1,11 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "SemanticSegmentor"
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
 DATASETS:
  TRAIN: ("coco_2017_train_panoptic_stuffonly",)
  TEST: ("coco_2017_val_panoptic_stuffonly",)
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
--- a/configs/PascalVOC-Detection/faster_rcnn_R_50_C4.yaml
+++ b/configs/PascalVOC-Detection/faster_rcnn_R_50_C4.yaml
@@ -0,0 +1,18 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    NUM_CLASSES: 20
 INPUT:
  MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
  MIN_SIZE_TEST: 800
 DATASETS:
  TRAIN: ('voc_2007_trainval', 'voc_2012_trainval')
  TEST: ('voc_2007_test',)
 SOLVER:
  STEPS: (12000, 16000)
  MAX_ITER: 18000  # 17.4 epochs
  WARMUP_ITERS: 100
--- a/configs/PascalVOC-Detection/faster_rcnn_R_50_FPN.yaml
+++ b/configs/PascalVOC-Detection/faster_rcnn_R_50_FPN.yaml
@@ -0,0 +1,18 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: False
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    NUM_CLASSES: 20
 INPUT:
  MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
  MIN_SIZE_TEST: 800
 DATASETS:
  TRAIN: ('voc_2007_trainval', 'voc_2012_trainval')
  TEST: ('voc_2007_test',)
 SOLVER:
  STEPS: (12000, 16000)
  MAX_ITER: 18000  # 17.4 epochs
  WARMUP_ITERS: 100
--- a/configs/quick_schedules/README.md
+++ b/configs/quick_schedules/README.md
@@ -0,0 +1 @@
 These are quick configs for performance or accuracy regression tracking purposes.
--- a/configs/quick_schedules/fast_rcnn_R_50_FPN_inference_acc_test.yaml
+++ b/configs/quick_schedules/fast_rcnn_R_50_FPN_inference_acc_test.yaml
@@ -0,0 +1,7 @@
 _BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/model_final_e5f7ce.pkl"
 DATASETS:
  TEST: ("coco_2017_val_100",)
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 45.70, 0.02]]
--- a/configs/quick_schedules/fast_rcnn_R_50_FPN_instant_test.yaml
+++ b/configs/quick_schedules/fast_rcnn_R_50_FPN_instant_test.yaml
@@ -0,0 +1,15 @@
 _BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
 DATASETS:
  TRAIN: ("coco_2017_val_100",)
  PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
  TEST: ("coco_2017_val_100",)
  PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
 SOLVER:
  BASE_LR: 0.005
  STEPS: (30,)
  MAX_ITER: 40
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/keypoint_rcnn_R_50_FPN_inference_acc_test.yaml
+++ b/configs/quick_schedules/keypoint_rcnn_R_50_FPN_inference_acc_test.yaml
@@ -0,0 +1,7 @@
 _BASE_: "../COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x/137849621/model_final_a6e10b.pkl"
 DATASETS:
  TEST: ("keypoints_coco_2017_val_100",)
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 52.47, 0.02], ["keypoints", "AP", 67.36, 0.02]]
--- a/configs/quick_schedules/keypoint_rcnn_R_50_FPN_instant_test.yaml
+++ b/configs/quick_schedules/keypoint_rcnn_R_50_FPN_instant_test.yaml
@@ -0,0 +1,14 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  KEYPOINT_ON: True
 DATASETS:
  TRAIN: ("keypoints_coco_2017_val_100",)
  TEST: ("keypoints_coco_2017_val_100",)
 SOLVER:
  BASE_LR: 0.005
  STEPS: (30,)
  MAX_ITER: 40
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/keypoint_rcnn_R_50_FPN_normalized_training_acc_test.yaml
+++ b/configs/quick_schedules/keypoint_rcnn_R_50_FPN_normalized_training_acc_test.yaml
@@ -0,0 +1,30 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  KEYPOINT_ON: True
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 256
    NUM_CLASSES: 1
  ROI_KEYPOINT_HEAD:
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 2
    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: False
    LOSS_WEIGHT: 4.0
  ROI_BOX_HEAD:
    SMOOTH_L1_BETA: 1.0  # Keypoint AP degrades when using plain L1 loss
  RPN:
    SMOOTH_L1_BETA: 0.2  # Keypoint AP degrades when using plain L1 loss
 DATASETS:
  TRAIN: ("keypoints_coco_2017_val",)
  TEST: ("keypoints_coco_2017_val",)
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
 SOLVER:
  WARMUP_FACTOR: 0.33333333
  WARMUP_ITERS: 100
  STEPS: (5500, 5800)
  MAX_ITER: 6000
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 55.35, 1.0], ["keypoints", "AP", 76.91, 1.0]]
--- a/configs/quick_schedules/keypoint_rcnn_R_50_FPN_training_acc_test.yaml
+++ b/configs/quick_schedules/keypoint_rcnn_R_50_FPN_training_acc_test.yaml
@@ -0,0 +1,28 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  KEYPOINT_ON: True
  RESNETS:
    DEPTH: 50
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 256
    NUM_CLASSES: 1
  ROI_KEYPOINT_HEAD:
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 2
  ROI_BOX_HEAD:
    SMOOTH_L1_BETA: 1.0  # Keypoint AP degrades when using plain L1 loss
  RPN:
    SMOOTH_L1_BETA: 0.2  # Keypoint AP degrades when using plain L1 loss
 DATASETS:
  TRAIN: ("keypoints_coco_2017_val",)
  TEST: ("keypoints_coco_2017_val",)
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
 SOLVER:
  WARMUP_FACTOR: 0.33333333
  WARMUP_ITERS: 100
  STEPS: (5500, 5800)
  MAX_ITER: 6000
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 53.5, 1.0], ["keypoints", "AP", 72.4, 1.0]]
--- a/configs/quick_schedules/mask_rcnn_R_50_C4_inference_acc_test.yaml
+++ b/configs/quick_schedules/mask_rcnn_R_50_C4_inference_acc_test.yaml
@@ -0,0 +1,7 @@
 _BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x/137849525/model_final_4ce675.pkl"
 DATASETS:
  TEST: ("coco_2017_val_100",)
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 47.37, 0.02], ["segm", "AP", 40.99, 0.02]]
--- a/configs/quick_schedules/mask_rcnn_R_50_C4_instant_test.yaml
+++ b/configs/quick_schedules/mask_rcnn_R_50_C4_instant_test.yaml
@@ -0,0 +1,14 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
 DATASETS:
  TRAIN: ("coco_2017_val_100",)
  TEST: ("coco_2017_val_100",)
 SOLVER:
  BASE_LR: 0.001
  STEPS: (30,)
  MAX_ITER: 40
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/mask_rcnn_R_50_C4_training_acc_test.yaml
+++ b/configs/quick_schedules/mask_rcnn_R_50_C4_training_acc_test.yaml
@@ -0,0 +1,22 @@
 _BASE_: "../Base-RCNN-C4.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 256
  MASK_ON: True
 DATASETS:
  TRAIN: ("coco_2017_val",)
  TEST: ("coco_2017_val",)
 INPUT:
  MIN_SIZE_TRAIN: (600,)
  MAX_SIZE_TRAIN: 1000
  MIN_SIZE_TEST: 800
  MAX_SIZE_TEST: 1000
 SOLVER:
  IMS_PER_BATCH: 8  # base uses 16
  WARMUP_FACTOR: 0.33333
  WARMUP_ITERS: 100
  STEPS: (11000, 11600)
  MAX_ITER: 12000
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 41.88, 0.7], ["segm", "AP", 33.79, 0.5]]
--- a/configs/quick_schedules/mask_rcnn_R_50_DC5_inference_acc_test.yaml
+++ b/configs/quick_schedules/mask_rcnn_R_50_DC5_inference_acc_test.yaml
@@ -0,0 +1,7 @@
 _BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x/137849551/model_final_84107b.pkl"
 DATASETS:
  TEST: ("coco_2017_val_100",)
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 47.44, 0.02], ["segm", "AP", 42.94, 0.02]]
--- a/configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml
+++ b/configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml
@@ -0,0 +1,11 @@
 _BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"
 DATASETS:
  TEST: ("coco_2017_val_100",)
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 47.34, 0.02], ["segm", "AP",  42.67, 0.02]]
  # expected results do not use test-time augmentation. TTA results are not verified.
  AUG:
    ENABLED: True
    MIN_SIZES: (400, 500)  # to save some time
--- a/configs/quick_schedules/mask_rcnn_R_50_FPN_instant_test.yaml
+++ b/configs/quick_schedules/mask_rcnn_R_50_FPN_instant_test.yaml
@@ -0,0 +1,14 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
 DATASETS:
  TRAIN: ("coco_2017_val_100",)
  TEST: ("coco_2017_val_100",)
 SOLVER:
  BASE_LR: 0.005
  STEPS: (30,)
  MAX_ITER: 40
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/mask_rcnn_R_50_FPN_training_acc_test.yaml
+++ b/configs/quick_schedules/mask_rcnn_R_50_FPN_training_acc_test.yaml
@@ -0,0 +1,21 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 256
  MASK_ON: True
 DATASETS:
  TRAIN: ("coco_2017_val",)
  TEST: ("coco_2017_val",)
 INPUT:
  MIN_SIZE_TRAIN: (600,)
  MAX_SIZE_TRAIN: 1000
  MIN_SIZE_TEST: 800
  MAX_SIZE_TEST: 1000
 SOLVER:
  WARMUP_FACTOR: 0.3333333
  WARMUP_ITERS: 100
  STEPS: (5500, 5800)
  MAX_ITER: 6000
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 42.8, 0.8], ["segm", "AP", 35.7, 0.8]]
--- a/configs/quick_schedules/panoptic_fpn_R_50_inference_acc_test.yaml
+++ b/configs/quick_schedules/panoptic_fpn_R_50_inference_acc_test.yaml
@@ -0,0 +1,7 @@
 _BASE_: "../COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-PanopticSegmentation/panoptic_fpn_R_50_3x/139514569/model_final_c10459.pkl"
 DATASETS:
  TEST: ("coco_2017_val_100_panoptic_separated",)
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 46.47, 0.02], ["segm", "AP", 43.39, 0.02], ["sem_seg", "mIoU", 42.55, 0.02], ["panoptic_seg", "PQ", 38.99, 0.02]]
--- a/configs/quick_schedules/panoptic_fpn_R_50_instant_test.yaml
+++ b/configs/quick_schedules/panoptic_fpn_R_50_instant_test.yaml
@@ -0,0 +1,19 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "PanopticFPN"
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
  SEM_SEG_HEAD:
    LOSS_WEIGHT: 0.5
 DATASETS:
  TRAIN: ("coco_2017_val_100_panoptic_separated",)
  TEST: ("coco_2017_val_100_panoptic_separated",)
 SOLVER:
  BASE_LR: 0.005
  STEPS: (30,)
  MAX_ITER: 40
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/panoptic_fpn_R_50_training_acc_test.yaml
+++ b/configs/quick_schedules/panoptic_fpn_R_50_training_acc_test.yaml
@@ -0,0 +1,20 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "PanopticFPN"
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  MASK_ON: True
  RESNETS:
    DEPTH: 50
  SEM_SEG_HEAD:
    LOSS_WEIGHT: 0.5
 DATASETS:
  TRAIN: ("coco_2017_val_panoptic_separated",)
  TEST: ("coco_2017_val_panoptic_separated",)
 SOLVER:
  BASE_LR: 0.01
  WARMUP_FACTOR: 0.001
  WARMUP_ITERS: 500
  STEPS: (5500,)
  MAX_ITER: 7000
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 46.80, 1.1], ["segm", "AP", 38.93, 0.7], ["sem_seg", "mIoU", 63.99, 0.9], ["panoptic_seg", "PQ", 48.23, 0.8]]
--- a/configs/quick_schedules/retinanet_R_50_FPN_inference_acc_test.yaml
+++ b/configs/quick_schedules/retinanet_R_50_FPN_inference_acc_test.yaml
@@ -0,0 +1,7 @@
 _BASE_: "../COCO-Detection/retinanet_R_50_FPN_3x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-Detection/retinanet_R_50_FPN_3x/137849486/model_final_4cafe0.pkl"
 DATASETS:
  TEST: ("coco_2017_val_100",)
 TEST:
  EXPECTED_RESULTS: [["bbox", "AP", 44.36, 0.02]]
--- a/configs/quick_schedules/retinanet_R_50_FPN_instant_test.yaml
+++ b/configs/quick_schedules/retinanet_R_50_FPN_instant_test.yaml
@@ -0,0 +1,13 @@
 _BASE_: "../COCO-Detection/retinanet_R_50_FPN_1x.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
 DATASETS:
  TRAIN: ("coco_2017_val_100",)
  TEST: ("coco_2017_val_100",)
 SOLVER:
  BASE_LR: 0.005
  STEPS: (30,)
  MAX_ITER: 40
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/rpn_R_50_FPN_inference_acc_test.yaml
+++ b/configs/quick_schedules/rpn_R_50_FPN_inference_acc_test.yaml
@@ -0,0 +1,7 @@
 _BASE_: "../COCO-Detection/rpn_R_50_FPN_1x.yaml"
 MODEL:
  WEIGHTS: "detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/model_final_02ce48.pkl"
 DATASETS:
  TEST: ("coco_2017_val_100",)
 TEST:
  EXPECTED_RESULTS: [["box_proposals", "AR@1000", 58.16, 0.02]]
--- a/configs/quick_schedules/rpn_R_50_FPN_instant_test.yaml
+++ b/configs/quick_schedules/rpn_R_50_FPN_instant_test.yaml
@@ -0,0 +1,13 @@
 _BASE_: "../COCO-Detection/rpn_R_50_FPN_1x.yaml"
 MODEL:
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
 DATASETS:
  TRAIN: ("coco_2017_val_100",)
  TEST: ("coco_2017_val_100",)
 SOLVER:
  STEPS: (30,)
  MAX_ITER: 40
  BASE_LR: 0.005
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/semantic_R_50_FPN_inference_acc_test.yaml
+++ b/configs/quick_schedules/semantic_R_50_FPN_inference_acc_test.yaml
@@ -0,0 +1,10 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "SemanticSegmentor"
  WEIGHTS: "detectron2://semantic_R_50_FPN_1x/111802073/model_final_c18079783c55a94968edc28b7101c5f0.pkl"
  RESNETS:
    DEPTH: 50
 DATASETS:
  TEST: ("coco_2017_val_100_panoptic_stuffonly",)
 TEST:
  EXPECTED_RESULTS: [["sem_seg", "mIoU", 39.53, 0.02], ["sem_seg", "mACC", 51.50, 0.02]]
--- a/configs/quick_schedules/semantic_R_50_FPN_instant_test.yaml
+++ b/configs/quick_schedules/semantic_R_50_FPN_instant_test.yaml
@@ -0,0 +1,18 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "SemanticSegmentor"
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
 DATASETS:
  TRAIN: ("coco_2017_val_100_panoptic_stuffonly",)
  TEST: ("coco_2017_val_100_panoptic_stuffonly",)
 INPUT:
  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
 SOLVER:
  BASE_LR: 0.005
  STEPS: (30,)
  MAX_ITER: 40
  IMS_PER_BATCH: 4
 DATALOADER:
  NUM_WORKERS: 2
--- a/configs/quick_schedules/semantic_R_50_FPN_training_acc_test.yaml
+++ b/configs/quick_schedules/semantic_R_50_FPN_training_acc_test.yaml
@@ -0,0 +1,20 @@
 _BASE_: "../Base-RCNN-FPN.yaml"
 MODEL:
  META_ARCHITECTURE: "SemanticSegmentor"
  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
  RESNETS:
    DEPTH: 50
 DATASETS:
  TRAIN: ("coco_2017_val_panoptic_stuffonly",)
  TEST: ("coco_2017_val_panoptic_stuffonly",)
 SOLVER:
  BASE_LR: 0.01
  WARMUP_FACTOR: 0.001
  WARMUP_ITERS: 300
  STEPS: (5500,)
  MAX_ITER: 7000
 TEST:
  EXPECTED_RESULTS: [["sem_seg", "mIoU", 76.51, 1.0], ["sem_seg", "mACC", 83.25, 1.0]]
 INPUT:
  # no scale augmentation
  MIN_SIZE_TRAIN: (800, )
--- a/datasets/README.md
+++ b/datasets/README.md
@@ -0,0 +1,85 @@

 For a few datasets that detectron2 natively supports,
 the datasets are assumed to exist in a directory called
 "datasets/", under the directory where you launch the program.
 They need to have the following directory structure:

 ## Expected dataset structure for COCO instance/keypoint detection:

 ```
 coco/
  annotations/
    instances_{train,val}2017.json
    person_keypoints_{train,val}2017.json
  {train,val}2017/
    # image files that are mentioned in the corresponding json
 ```

 You can use the 2014 version of the dataset as well.

 Some of the builtin tests (`dev/run_*_tests.sh`) uses a tiny version of the COCO dataset,
 which you can download with `./prepare_for_tests.sh`.

 ## Expected dataset structure for PanopticFPN:

 ```
 coco/
  annotations/
    panoptic_{train,val}2017.json
  panoptic_{train,val}2017/
    # png annotations
  panoptic_stuff_{train,val}2017/  # generated by the script mentioned below
 ```

 Install panopticapi by:
 ```
 pip install git+https://github.com/cocodataset/panopticapi.git
 ```
 Then, run `python prepare_panoptic_fpn.py`, to extract semantic annotations from panoptic annotations.

 ## Expected dataset structure for LVIS instance segmentation:
 ```
 coco/
  {train,val,test}2017/
 lvis/
  lvis_v0.5_{train,val}.json
  lvis_v0.5_image_info_test.json
 ```

 Install lvis-api by:
 ```
 pip install git+https://github.com/lvis-dataset/lvis-api.git
 ```

 ## Expected dataset structure for cityscapes:
 ```
 cityscapes/
  gtFine/
    train/
      aachen/
        color.png, instanceIds.png, labelIds.png, polygons.json,
        labelTrainIds.png
      ...
    val/
    test/
  leftImg8bit/
    train/
    val/
    test/
 ```
 Install cityscapes scripts by:
 ```
 pip install git+https://github.com/mcordts/cityscapesScripts.git
 ```

 Note:
 labelTrainIds.png are created by `cityscapesscripts/preparation/createTrainIdLabelImgs.py`.
 They are not needed for instance segmentation.

 ## Expected dataset structure for Pascal VOC:
 ```
 VOC20{07,12}/
  Annotations/
  ImageSets/
  JPEGImages/
 ```
--- a/datasets/prepare_for_tests.sh
+++ b/datasets/prepare_for_tests.sh
@@ -0,0 +1,22 @@
 #!/bin/bash -e
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved

 # Download some files needed for running tests.

 cd "${0%/*}"

 BASE=https://dl.fbaipublicfiles.com/detectron2
 mkdir -p coco/annotations

 for anno in instances_val2017_100 \
  person_keypoints_val2017_100 \
  instances_minival2014_100 \
  person_keypoints_minival2014_100; do

  dest=coco/annotations/$anno.json
  [[ -s $dest ]] && {
    echo "$dest exists. Skipping ..."
  } || {
    wget $BASE/annotations/coco/$anno.json -O $dest
  }
 done
--- a/datasets/prepare_panoptic_fpn.py
+++ b/datasets/prepare_panoptic_fpn.py
@@ -0,0 +1,116 @@
 # -*- coding: utf-8 -*-
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved

 import time
 import functools
 import json
 import multiprocessing as mp
 import numpy as np
 import os
 from PIL import Image

 from detectron2.data.datasets.builtin_meta import COCO_CATEGORIES
 from fvcore.common.download import download

 from panopticapi.utils import rgb2id


 def _process_panoptic_to_semantic(input_panoptic, output_semantic, segments, id_map):
    panoptic = np.asarray(Image.open(input_panoptic), dtype=np.uint32)
    panoptic = rgb2id(panoptic)
    output = np.zeros_like(panoptic, dtype=np.uint8) + 255
    for seg in segments:
        cat_id = seg["category_id"]
        new_cat_id = id_map[cat_id]
        output[panoptic == seg["id"]] = new_cat_id
    Image.fromarray(output).save(output_semantic)


 def separate_coco_semantic_from_panoptic(panoptic_json, panoptic_root, sem_seg_root, categories):
    """
    Create semantic segmentation annotations from panoptic segmentation
    annotations, to be used by PanopticFPN.

    It maps all thing categories to class 0, and maps all unlabeled pixels to class 255.
    It maps all stuff categories to contiguous ids starting from 1.

    Args:
        panoptic_json (str): path to the panoptic json file, in COCO's format.
        panoptic_root (str): a directory with panoptic annotation files, in COCO's format.
        sem_seg_root (str): a directory to output semantic annotation files
        categories (list[dict]): category metadata. Each dict needs to have:
            "id": corresponds to the "category_id" in the json annotations
            "isthing": 0 or 1
    """
    os.makedirs(sem_seg_root, exist_ok=True)

    stuff_ids = [k["id"] for k in categories if k["isthing"] == 0]
    thing_ids = [k["id"] for k in categories if k["isthing"] == 1]
    id_map = {}  # map from category id to id in the output semantic annotation
    assert len(stuff_ids) <= 254
    for i, stuff_id in enumerate(stuff_ids):
        id_map[stuff_id] = i + 1
    for thing_id in thing_ids:
        id_map[thing_id] = 0
    id_map[0] = 255

    with open(panoptic_json) as f:
        obj = json.load(f)

    pool = mp.Pool(processes=max(mp.cpu_count() // 2, 4))

    def iter_annotations():
        for anno in obj["annotations"]:
            file_name = anno["file_name"]
            segments = anno["segments_info"]
            input = os.path.join(panoptic_root, file_name)
            output = os.path.join(sem_seg_root, file_name)
            yield input, output, segments

    print("Start writing to {} ...".format(sem_seg_root))
    start = time.time()
    pool.starmap(
        functools.partial(_process_panoptic_to_semantic, id_map=id_map),
        iter_annotations(),
        chunksize=100,
    )
    print("Finished. time: {:.2f}s".format(time.time() - start))


 if __name__ == "__main__":
    dataset_dir = os.path.join(os.path.dirname(__file__), "coco")
    for s in ["val2017", "train2017"]:
        separate_coco_semantic_from_panoptic(
            os.path.join(dataset_dir, "annotations/panoptic_{}.json".format(s)),
            os.path.join(dataset_dir, "panoptic_{}".format(s)),
            os.path.join(dataset_dir, "panoptic_stuff_{}".format(s)),
            COCO_CATEGORIES,
        )

    # Prepare val2017_100 for quick testing:

    dest_dir = os.path.join(dataset_dir, "annotations/")
    URL_PREFIX = "https://dl.fbaipublicfiles.com/detectron2/"
    download(URL_PREFIX + "annotations/coco/panoptic_val2017_100.json", dest_dir)
    with open(os.path.join(dest_dir, "panoptic_val2017_100.json")) as f:
        obj = json.load(f)

    def link_val100(dir_full, dir_100):
        print("Creating " + dir_100 + " ...")
        os.makedirs(dir_100, exist_ok=True)
        for img in obj["images"]:
            basename = os.path.splitext(img["file_name"])[0]
            src = os.path.join(dir_full, basename + ".png")
            dst = os.path.join(dir_100, basename + ".png")
            src = os.path.relpath(src, start=dir_100)
            os.symlink(src, dst)

    link_val100(
        os.path.join(dataset_dir, "panoptic_val2017"),
        os.path.join(dataset_dir, "panoptic_val2017_100"),
    )

    link_val100(
        os.path.join(dataset_dir, "panoptic_stuff_val2017"),
        os.path.join(dataset_dir, "panoptic_stuff_val2017_100"),
    )
--- a/demo/README.md
+++ b/demo/README.md
@@ -0,0 +1,8 @@

 ## Detectron2 Demo

 We provide a command line tools for running a simple demo.
 The usage is explained in [GETTING_STARTED.md](../GETTING_STARTED.md).

 See our [blog post](https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-)
 for a high-quality demo generated with this tool.
--- a/demo/demo.py
+++ b/demo/demo.py
@@ -0,0 +1,149 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
 import argparse
 import glob
 import multiprocessing as mp
 import os
 import time
 import cv2
 import tqdm

 from detectron2.config import get_cfg
 from detectron2.data.detection_utils import read_image
 from detectron2.utils.logger import setup_logger

 from predictor import VisualizationDemo

 # constants
 WINDOW_NAME = "COCO detections"


 def setup_cfg(args):
    # load config from file and command-line arguments
    cfg = get_cfg()
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    # Set score_threshold for builtin models
    cfg.MODEL.RETINANET.SCORE_THRESH_TEST = args.confidence_threshold
    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = args.confidence_threshold
    cfg.MODEL.PANOPTIC_FPN.COMBINE.INSTANCES_CONFIDENCE_THRESH = args.confidence_threshold
    cfg.freeze()
    return cfg


 def get_parser():
    parser = argparse.ArgumentParser(description="Detectron2 Demo")
    parser.add_argument(
        "--config-file",
        default="configs/quick_schedules/e2e_mask_rcnn_R_50_FPN_inference_acc_test.yaml",
        metavar="FILE",
        help="path to config file",
    )
    parser.add_argument("--webcam", action="store_true", help="Take inputs from webcam.")
    parser.add_argument("--video-input", help="Path to video file.")
    parser.add_argument("--input", nargs="+", help="A list of space separated input images")
    parser.add_argument(
        "--output",
        help="A file or directory to save output visualizations. "
        "If not given, will show output in an OpenCV window.",
    )

    parser.add_argument(
        "--confidence-threshold",
        type=float,
        default=0.5,
        help="Minimum score for instance predictions to be shown",
    )
    parser.add_argument(
        "--opts",
        help="Modify config options using the command-line 'KEY VALUE' pairs",
        default=[],
        nargs=argparse.REMAINDER,
    )
    return parser


 if __name__ == "__main__":
    mp.set_start_method("spawn", force=True)
    args = get_parser().parse_args()
    logger = setup_logger()
    logger.info("Arguments: " + str(args))

    cfg = setup_cfg(args)

    demo = VisualizationDemo(cfg)

    if args.input:
        if len(args.input) == 1:
            args.input = glob.glob(os.path.expanduser(args.input[0]))
            assert args.input, "The input path(s) was not found"
        for path in tqdm.tqdm(args.input, disable=not args.output):
            # use PIL, to be consistent with evaluation
            img = read_image(path, format="BGR")
            start_time = time.time()
            predictions, visualized_output = demo.run_on_image(img)
            logger.info(
                "{}: detected {} instances in {:.2f}s".format(
                    path, len(predictions["instances"]), time.time() - start_time
                )
            )

            if args.output:
                if os.path.isdir(args.output):
                    assert os.path.isdir(args.output), args.output
                    out_filename = os.path.join(args.output, os.path.basename(path))
                else:
                    assert len(args.input) == 1, "Please specify a directory with args.output"
                    out_filename = args.output
                visualized_output.save(out_filename)
            else:
                cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
                cv2.imshow(WINDOW_NAME, visualized_output.get_image()[:, :, ::-1])
                if cv2.waitKey(0) == 27:
                    break  # esc to quit
    elif args.webcam:
        assert args.input is None, "Cannot have both --input and --webcam!"
        cam = cv2.VideoCapture(0)
        for vis in tqdm.tqdm(demo.run_on_video(cam)):
            cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
            cv2.imshow(WINDOW_NAME, vis)
            if cv2.waitKey(1) == 27:
                break  # esc to quit
        cv2.destroyAllWindows()
    elif args.video_input:
        video = cv2.VideoCapture(args.video_input)
        width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
        height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
        frames_per_second = video.get(cv2.CAP_PROP_FPS)
        num_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
        basename = os.path.basename(args.video_input)

        if args.output:
            if os.path.isdir(args.output):
                output_fname = os.path.join(args.output, basename)
                output_fname = os.path.splitext(output_fname)[0] + ".mkv"
            else:
                output_fname = args.output
            assert not os.path.isfile(output_fname), output_fname
            output_file = cv2.VideoWriter(
                filename=output_fname,
                # some installation of opencv may not support x264 (due to its license),
                # you can try other format (e.g. MPEG)
                fourcc=cv2.VideoWriter_fourcc(*"x264"),
                fps=float(frames_per_second),
                frameSize=(width, height),
                isColor=True,
            )
        assert os.path.isfile(args.video_input)
        for vis_frame in tqdm.tqdm(demo.run_on_video(video), total=num_frames):
            if args.output:
                output_file.write(vis_frame)
            else:
                cv2.namedWindow(basename, cv2.WINDOW_NORMAL)
                cv2.imshow(basename, vis_frame)
                if cv2.waitKey(1) == 27:
                    break  # esc to quit
        video.release()
        if args.output:
            output_file.release()
        else:
            cv2.destroyAllWindows()
--- a/demo/predictor.py
+++ b/demo/predictor.py
@@ -0,0 +1,220 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
 import atexit
 import bisect
 import multiprocessing as mp
 from collections import deque
 import cv2
 import torch

 from detectron2.data import MetadataCatalog
 from detectron2.engine.defaults import DefaultPredictor
 from detectron2.utils.video_visualizer import VideoVisualizer
 from detectron2.utils.visualizer import ColorMode, Visualizer


 class VisualizationDemo(object):
    def __init__(self, cfg, instance_mode=ColorMode.IMAGE, parallel=False):
        """
        Args:
            cfg (CfgNode):
            instance_mode (ColorMode):
            parallel (bool): whether to run the model in different processes from visualization.
                Useful since the visualization logic can be slow.
        """
        self.metadata = MetadataCatalog.get(
            cfg.DATASETS.TEST[0] if len(cfg.DATASETS.TEST) else "__unused"
        )
        self.cpu_device = torch.device("cpu")
        self.instance_mode = instance_mode

        self.parallel = parallel
        if parallel:
            num_gpu = torch.cuda.device_count()
            self.predictor = AsyncPredictor(cfg, num_gpus=num_gpu)
        else:
            self.predictor = DefaultPredictor(cfg)

    def run_on_image(self, image):
        """
        Args:
            image (np.ndarray): an image of shape (H, W, C) (in BGR order).
                This is the format used by OpenCV.

        Returns:
            predictions (dict): the output of the model.
            vis_output (VisImage): the visualized image output.
        """
        vis_output = None
        predictions = self.predictor(image)
        # Convert image from OpenCV BGR format to Matplotlib RGB format.
        image = image[:, :, ::-1]
        visualizer = Visualizer(image, self.metadata, instance_mode=self.instance_mode)
        if "panoptic_seg" in predictions:
            panoptic_seg, segments_info = predictions["panoptic_seg"]
            vis_output = visualizer.draw_panoptic_seg_predictions(
                panoptic_seg.to(self.cpu_device), segments_info
            )
        else:
            if "sem_seg" in predictions:
                vis_output = visualizer.draw_sem_seg(
                    predictions["sem_seg"].argmax(dim=0).to(self.cpu_device)
                )
            if "instances" in predictions:
                instances = predictions["instances"].to(self.cpu_device)
                vis_output = visualizer.draw_instance_predictions(predictions=instances)

        return predictions, vis_output

    def _frame_from_video(self, video):
        while video.isOpened():
            success, frame = video.read()
            if success:
                yield frame
            else:
                break

    def run_on_video(self, video):
        """
        Visualizes predictions on frames of the input video.

        Args:
            video (cv2.VideoCapture): a :class:`VideoCapture` object, whose source can be
                either a webcam or a video file.

        Yields:
            ndarray: BGR visualizations of each video frame.
        """
        video_visualizer = VideoVisualizer(self.metadata, self.instance_mode)

        def process_predictions(frame, predictions):
            frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
            if "panoptic_seg" in predictions:
                panoptic_seg, segments_info = predictions["panoptic_seg"]
                vis_frame = video_visualizer.draw_panoptic_seg_predictions(
                    frame, panoptic_seg.to(self.cpu_device), segments_info
                )
            elif "instances" in predictions:
                predictions = predictions["instances"].to(self.cpu_device)
                vis_frame = video_visualizer.draw_instance_predictions(frame, predictions)
            elif "sem_seg" in predictions:
                vis_frame = video_visualizer.draw_sem_seg(
                    frame, predictions["sem_seg"].argmax(dim=0).to(self.cpu_device)
                )

            # Converts Matplotlib RGB format to OpenCV BGR format
            vis_frame = cv2.cvtColor(vis_frame.get_image(), cv2.COLOR_RGB2BGR)
            return vis_frame

        frame_gen = self._frame_from_video(video)
        if self.parallel:
            buffer_size = self.predictor.default_buffer_size

            frame_data = deque()

            for cnt, frame in enumerate(frame_gen):
                frame_data.append(frame)
                self.predictor.put(frame)

                if cnt >= buffer_size:
                    frame = frame_data.popleft()
                    predictions = self.predictor.get()
                    yield process_predictions(frame, predictions)

            while len(frame_data):
                frame = frame_data.popleft()
                predictions = self.predictor.get()
                yield process_predictions(frame, predictions)
        else:
            for frame in frame_gen:
                yield process_predictions(frame, self.predictor(frame))


 class AsyncPredictor:
    """
    A predictor that runs the model asynchronously, possibly on >1 GPUs.
    Because rendering the visualization takes considerably amount of time,
    this helps improve throughput when rendering videos.
    """

    class _StopToken:
        pass

    class _PredictWorker(mp.Process):
        def __init__(self, cfg, task_queue, result_queue):
            self.cfg = cfg
            self.task_queue = task_queue
            self.result_queue = result_queue
            super().__init__()

        def run(self):
            predictor = DefaultPredictor(self.cfg)

            while True:
                task = self.task_queue.get()
                if isinstance(task, AsyncPredictor._StopToken):
                    break
                idx, data = task
                result = predictor(data)
                self.result_queue.put((idx, result))

    def __init__(self, cfg, num_gpus: int = 1):
        """
        Args:
            cfg (CfgNode):
            num_gpus (int): if 0, will run on CPU
        """
        num_workers = max(num_gpus, 1)
        self.task_queue = mp.Queue(maxsize=num_workers * 3)
        self.result_queue = mp.Queue(maxsize=num_workers * 3)
        self.procs = []
        for gpuid in range(max(num_gpus, 1)):
            cfg = cfg.clone()
            cfg.defrost()
            cfg.MODEL.DEVICE = "cuda:{}".format(gpuid) if num_gpus > 0 else "cpu"
            self.procs.append(
                AsyncPredictor._PredictWorker(cfg, self.task_queue, self.result_queue)
            )

        self.put_idx = 0
        self.get_idx = 0
        self.result_rank = []
        self.result_data = []

        for p in self.procs:
            p.start()
        atexit.register(self.shutdown)

    def put(self, image):
        self.put_idx += 1
        self.task_queue.put((self.put_idx, image))

    def get(self):
        self.get_idx += 1  # the index needed for this request
        if len(self.result_rank) and self.result_rank[0] == self.get_idx:
            res = self.result_data[0]
            del self.result_data[0], self.result_rank[0]
            return res

        while True:
            # make sure the results are returned in the correct order
            idx, res = self.result_queue.get()
            if idx == self.get_idx:
                return res
            insert = bisect.bisect(self.result_rank, idx)
            self.result_rank.insert(insert, idx)
            self.result_data.insert(insert, res)

    def __len__(self):
        return self.put_idx - self.get_idx

    def __call__(self, image):
        self.put(image)
        return self.get()

    def shutdown(self):
        for _ in self.procs:
            self.task_queue.put(AsyncPredictor._StopToken())

    @property
    def default_buffer_size(self):
        return len(self.procs) * 5
--- a/detectron2/init.py
+++ b/detectron2/init.py
@@ -0,0 +1,8 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 from .utils.env import setup_environment

 setup_environment()


 __version__ = "0.1"
--- a/detectron2/checkpoint/init.py
+++ b/detectron2/checkpoint/init.py
@@ -0,0 +1,10 @@
 # -*- coding: utf-8 -*-
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
 # File:


 from . import catalog as _UNUSED  # register the handler
 from .detection_checkpoint import DetectionCheckpointer
 from fvcore.common.checkpoint import Checkpointer, PeriodicCheckpointer

 __all__ = ["Checkpointer", "PeriodicCheckpointer", "DetectionCheckpointer"]