Huawei_Technology
/
mindspore
Not watched
1
0
Fork 0
Code
Releases 13 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
Browse Source

!4917 Modify readme for inceptionv3 

Merge pull request !4917 from zhouyaqiang0/master
tags/v0.7.0-beta
mindspore-ci-bot Gitee 5 years ago
parent
95f89e710e aba52a459e
commit
72efb63fd8
2 changed files with 152 additions and 40 deletions
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +151
    -39
      model_zoo/official/cv/inceptionv3/README.md
  2. +1
    -1
      model_zoo/official/cv/inceptionv3/src/config.py

+ 151
- 39
model_zoo/official/cv/inceptionv3/README.md View File

@@ -1,23 +1,77 @@
# Inception-v3 Example
# Contents


## Description
- [InceptionV3 Description](#InceptionV3-description)
- [Model Architecture](#model-architecture)
- [Dataset](#dataset)
- [Features](#features)
- [Mixed Precision](#mixed-precision)
- [Environment Requirements](#environment-requirements)
- [Script Description](#script-description)
- [Script and Sample Code](#script-and-sample-code)
- [Training Process](#training-process)
- [Evaluation Process](#evaluation-process)
- [Evaluation](#evaluation)
- [Model Description](#model-description)
- [Performance](#performance)
- [Training Performance](#evaluation-performance)
- [Inference Performance](#evaluation-performance)
- [Description of Random Situation](#description-of-random-situation)
- [ModelZoo Homepage](#modelzoo-homepage)


This is an example of training Inception-v3 in MindSpore.
# [InceptionV3 Description](#contents)


## Requirements
InceptionV3 by Google is the 3rd version in a series of Deep Learning Convolutional Architectures.


- Install [Mindspore](http://www.mindspore.cn/install/en).
- Downlaod the dataset.
[Paper](https://arxiv.org/pdf/1512.00567.pdf) Min Sun, Ali Farhadi, Steve Seitz. Ranking Domain-Specific Highlights by Analyzing Edited Videos[J]. 2014.


## Structure
# [Model architecture](#contents)

The overall network architecture of InceptionV3 is show below:

[Link](https://arxiv.org/pdf/1905.02244)


# [Dataset](#contents)

Dataset used can refer to paper.

- Dataset size: ~125G, 1.2W colorful images in 1000 classes
- Train: 120G, 1.2W images
- Test: 5G, 50000 images
- Data format: RGB images.
- Note: Data will be processed in src/dataset.py

# [Features](#contents)

## [Mixed Precision(Ascend)](#contents)

The [mixed precision](https://www.mindspore.cn/tutorial/zh-CN/master/advanced_use/mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data formats, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware.
For FP16 operators, if the input data type is FP32, the backend of MindSpore will automatically handle it with reduced precision. Users could check the reduced-precision operators by enabling INFO log and then searching ‘reduce precision’.

# [Environment Requirements](#contents)

- Hardware（Ascend/GPU）
- Prepare hardware environment with Ascend or GPU processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Framework
- [MindSpore](http://10.90.67.50/mindspore/archive/20200506/OpenSource/me_vm_x86/)
- For more information, please check the resources below：
- [MindSpore tutorials](https://www.mindspore.cn/tutorial/zh-CN/master/index.html)
- [MindSpore API](https://www.mindspore.cn/api/zh-CN/master/index.html)

# [Script description](#contents)

## [Script and sample code](#contents)


```shell ```shell
. .
└─Inception-v3 └─Inception-v3
├─README.md ├─README.md
├─scripts ├─scripts
├─run_standalone_train.sh # launch standalone training with ascend platform(1p)
├─run_standalone_train_for_gpu.sh # launch standalone training with gpu platform(1p) ├─run_standalone_train_for_gpu.sh # launch standalone training with gpu platform(1p)
├─run_distribute_train.sh # launch distributed training with ascend platform(8p)
├─run_distribute_train_for_gpu.sh # launch distributed training with gpu platform(8p) ├─run_distribute_train_for_gpu.sh # launch distributed training with gpu platform(8p)
├─run_eval.sh # launch evaluating with ascend platform
└─run_eval_for_gpu.sh # launch evaluating with gpu platform └─run_eval_for_gpu.sh # launch evaluating with gpu platform
├─src ├─src
├─config.py # parameter configuration ├─config.py # parameter configuration
@@ -30,12 +84,10 @@ This is an example of training Inception-v3 in MindSpore.
└─train.py # train net └─train.py # train net
``` ```
## [Script Parameters](#contents)


## Parameter Configuration

Parameters for both training and evaluating can be set in config.py

```
```python
Major parameters in train.py and config.py are:
'random_seed': 1, # fix random seed 'random_seed': 1, # fix random seed
'rank': 0, # local rank of distributed 'rank': 0, # local rank of distributed
'group_size': 1, # world size of distributed 'group_size': 1, # world size of distributed
@@ -59,14 +111,22 @@ Parameters for both training and evaluating can be set in config.py
'is_save_on_master': 1 # save checkpoint on rank0, distributed parameters 'is_save_on_master': 1 # save checkpoint on rank0, distributed parameters
``` ```


## [Training process](#contents)


### Usage


## Running the example


### Train
You can start training using python or shell scripts. The usage of shell scripts as follows:


#### Usage
- Ascend:
```
# distribute training example(8p)
sh run_distribute_train.sh RANK_TABLE_FILE DATA_PATH
# standalone training
sh run_standalone_train.sh DEVICE_ID DATA_PATH
```


- GPU:
``` ```
# distribute training example(8p) # distribute training example(8p)
sh run_distribute_train_for_gpu.sh DATA_DIR sh run_distribute_train_for_gpu.sh DATA_DIR
@@ -74,42 +134,94 @@ sh run_distribute_train_for_gpu.sh DATA_DIR
sh run_standalone_train_for_gpu.sh DEVICE_ID DATA_DIR sh run_standalone_train_for_gpu.sh DEVICE_ID DATA_DIR
``` ```


#### Launch
### Launch

```
# training example
python:
Ascend: python train.py --dataset_path /dataset/train --platform Ascend
GPU: python train.py --dataset_path /dataset/train --platform GPU


```bash
# distributed training example(8p) for GPU
sh scripts/run_distribute_train_for_gpu.sh /dataset/train
# standalone training example for GPU
sh scripts/run_standalone_train_for_gpu.sh 0 /dataset/train
shell:
# distributed training example(8p) for GPU
sh scripts/run_distribute_train_for_gpu.sh /dataset/train
# standalone training example for GPU
sh scripts/run_standalone_train_for_gpu.sh 0 /dataset/train
``` ```


#### Result
### Result


You can find checkpoint file together with result in log.
Training result will be stored in the example path. Checkpoints will be stored at `. /checkpoint` by default, and training log will be redirected to `./log.txt` like followings.


### Evaluation
```
epoch: 0 step: 1251, loss is 5.7787247
Epoch time: 360760.985, per step time: 288.378
epoch: 1 step: 1251, loss is 4.392868
Epoch time: 160917.911, per step time: 128.631
```
## [Eval process](#contents)


#### Usage
### Usage


You can start training using python or shell scripts. The usage of shell scripts as follows:

- Ascend: sh run_eval.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT
- GPU: sh run_eval_for_gpu.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT

### Launch

```
# eval example
python:
Ascend: python eval.py --dataset_path DATA_DIR --checkpoint PATH_CHECKPOINT --platform Ascend
GPU: python eval.py --dataset_path DATA_DIR --checkpoint PATH_CHECKPOINT --platform GPU

shell:
Ascend: sh run_eval.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT
GPU: sh run_eval_for_gpu.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT
``` ```
# Evaluation
sh run_eval_for_gpu.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT
```


#### Launch
> checkpoint can be produced in training process.

### Result


```bash
# Evaluation with checkpoint
sh scripts/run_eval_for_gpu.sh 0 /dataset/val ./checkpoint/inceptionv3-rank3-247_1251.ckpt
Evaluation result will be stored in the example path, you can find result like the followings in `log.txt`.

```
metric: {'Loss': 1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942}
``` ```


> checkpoint can be produced in training process.
# [Model description](#contents)

## [Performance](#contents)

### Training Performance

| Parameters | InceptionV3 | |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| Model Version | | |
| Resource | Ascend 910, cpu:2.60GHz 56cores, memory:314G | NV SMX2 V100-32G |
| uploaded Date | 08/21/2020 | 08/21/2020 |
| MindSpore Version | 0.6.0-beta | 0.6.0-beta |
| Training Parameters | src/config.py | src/config.py |
| Optimizer | RMSProp | RMSProp |
| Loss Function | SoftmaxCrossEntropy | SoftmaxCrossEntropy |
| outputs | probability | probability |
| Loss | 1.98 | 1.98 |
| Accuracy | ACC1[78.8%] ACC5[94.2%] | ACC1[78.7%] ACC5[94.1%] |
| Total time | 11h | 72h |
| Params (M) | 103M | 103M |
| Checkpoint for Fine tuning | 313M | 312.41 |
| Model for inference | | |


#### Result
#### Inference Performance


Evaluation result will be stored in the scripts path. Under this, you can find result like the followings in log.
To be added.

# [Description of Random Situation](#contents)

In dataset.py, we set the seed inside “create_dataset" function. We also use random seed in train.py.

# [ModelZoo Homepage](#contents)
```
acc=78.75%(TOP1)
acc=94.07%(TOP5)
```
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).

+ 1
- 1
model_zoo/official/cv/inceptionv3/src/config.py View File

@@ -64,7 +64,7 @@ config_ascend = edict({
'weight_decay': 0.00004, 'weight_decay': 0.00004,
'momentum': 0.9, 'momentum': 0.9,
'opt_eps': 1.0, 'opt_eps': 1.0,
'keep_checkpoint_max': 100,
'keep_checkpoint_max': 10,
'ckpt_path': './checkpoint/', 'ckpt_path': './checkpoint/',
'is_save_on_master': 0, 'is_save_on_master': 0,
'dropout_keep_prob': 0.8, 'dropout_keep_prob': 0.8,


Write Preview
Loading…
Cancel
Save