Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
|
|
4 years ago | |
|---|---|---|
| .. | ||
| scripts | 4 years ago | |
| src | 4 years ago | |
| README_CN.md | 4 years ago | |
| Readme.md | 4 years ago | |
| eval.py | 4 years ago | |
| export.py | 4 years ago | |
| mindspore_hub_conf.py | 5 years ago | |
| train.py | 4 years ago | |
MobileNetV3 is tuned to mobile phone CPUs through a combination of hardware- aware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances.Nov 20, 2019.
Paper Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for mobilenetv3." In Proceedings of the IEEE International Conference on Computer Vision, pp. 1314-1324. 2019.
The overall network architecture of MobileNetV3 is show below:
Dataset used: imagenet
├── MobileNetV3
├── Readme.md # descriptions about MobileNetV3
├── scripts
│ ├──run_train.sh # shell script for train
│ ├──run_eval.sh # shell script for evaluation
├── src
│ ├──config.py # parameter configuration
│ ├──dataset.py # creating dataset
│ ├──lr_generator.py # learning rate config
│ ├──mobilenetV3.py # MobileNetV3 architecture
├── train.py # training script
├── eval.py # evaluation script
├── export.py # export mindir script
├── mindspore_hub_conf.py # mindspore hub interface
You can start training using python or shell scripts. The usage of shell scripts as follows:
# training example
python:
GPU: python train.py --dataset_path ~/imagenet/train/ --device_targe GPU
CPU: python train.py --dataset_path ~/cifar10/train/ --device_targe CPU
shell:
GPU: sh run_train.sh GPU 8 0,1,2,3,4,5,6,7 ~/imagenet/train/
CPU: sh run_train.sh CPU ~/cifar10/train/
Training result will be stored in the example path. Checkpoints will be stored at . /checkpoint by default, and training log will be redirected to ./train/train.log like followings.
epoch: [ 0/200], step:[ 624/ 625], loss:[5.258/5.258], time:[140412.236], lr:[0.100]
epoch time: 140522.500, per step time: 224.836, avg loss: 5.258
epoch: [ 1/200], step:[ 624/ 625], loss:[3.917/3.917], time:[138221.250], lr:[0.200]
epoch time: 138331.250, per step time: 221.330, avg loss: 3.917
You can start training using python or shell scripts. The usage of shell scripts as follows:
# infer example
python:
GPU: python eval.py --dataset_path ~/imagenet/val/ --checkpoint_path mobilenet_199.ckpt --device_targe GPU
CPU: python eval.py --dataset_path ~/cifar10/val/ --checkpoint_path mobilenet_199.ckpt --device_targe CPU
shell:
GPU: sh run_infer.sh GPU ~/imagenet/val/ ~/train/mobilenet-200_625.ckpt
CPU: sh run_infer.sh CPU ~/cifar10/val/ ~/train/mobilenet-200_625.ckpt
checkpoint can be produced in training process.
Inference result will be stored in the example path, you can find result like the followings in val.log.
result: {'acc': 0.71976314102564111} ckpt=/path/to/checkpoint/mobilenet-200_625.ckpt
Change the export mode and export file in src/config.py, and run export.py.
python export.py --device_target [PLATFORM] --checkpoint_path [CKPT_PATH]
| Parameters | MobilenetV3 |
|---|---|
| Model Version | large |
| Resource | NV SMX2 V100-32G |
| uploaded Date | 05/06/2020 |
| MindSpore Version | 0.3.0 |
| Dataset | ImageNet |
| Training Parameters | src/config.py |
| Optimizer | Momentum |
| Loss Function | SoftmaxCrossEntropy |
| outputs | probability |
| Loss | 1.913 |
| Accuracy | ACC1[77.57%] ACC5[92.51%] |
| Total time | 1433 min |
| Params (M) | 5.48 M |
| Checkpoint for Fine tuning | 44 M |
| Scripts | Link |
In dataset.py, we set the seed inside “create_dataset" function. We also use random seed in train.py.
Please check the official homepage.
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
C++ Python Text Unity3D Asset C other