> Unzip the ImageNet2012 dataset to any path you want and the folder structure should be as follows:
> ```
> .
> ├── train # train dataset
> └── val # infer dataset
> ```
## Example structure
``` shell
.
├── config.py # parameter configuration
├── dataset.py # data preprocessing
├── eval.py # infer script
├── launch.py # launcher for distributed training
├── lr_generator.py # generate learning rate for each step
├── run_infer.sh # launch infering
├── run_train.sh # launch training
└── train.py # train script
```
## Parameter configuration
Parameters for both training and inference can be set in 'config.py'.
```
"num_classes": 1000, # dataset class num
"image_height": 224, # image height
"image_width": 224, # image width
"batch_size": 256, # training or infering batch size
"epoch_size": 200, # total training epochs, including warmup_epochs
"warmup_epochs": 4, # warmup epochs
"lr": 0.4, # base learning rate
"momentum": 0.9, # momentum
"weight_decay": 4e-5, # weight decay
"loss_scale": 1024, # loss scale
"save_checkpoint": True, # whether save checkpoint
"save_checkpoint_epochs": 1, # the epoch interval between two checkpoints
"keep_checkpoint_max": 200, # only keep the last keep_checkpoint_max checkpoint
"save_checkpoint_path": "./checkpoint" # path to save checkpoint
```
## Running the example
### Train
#### Usage
Usage: sh run_train.sh [DEVICE_NUM] [SERVER_IP(x.x.x.x)] [VISIABLE_DEVICES(0,1,2,3,4,5,6,7)] [DATASET_PATH]
#### Launch
```
# training example
sh run_train.sh 8 192.168.0.1 0,1,2,3,4,5,6,7 ~/imagenet
```
#### Result
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.
MobileNetV2 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](https://arxiv.org/pdf/1905.02244) Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for MobileNetV2." In Proceedings of the IEEE International Conference on Computer Vision, pp. 1314-1324. 2019.
# Model architecture
The overall network architecture of MobileNetV2 is show below:
- 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
# Environment Requirements
- 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.
- Ascend: sh run_train.sh Ascend [DEVICE_NUM] [SERVER_IP(x.x.x.x)] [VISIABLE_DEVICES(0,1,2,3,4,5,6,7)] [DATASET_PATH]
- GPU: sh run_trian.sh GPU [DEVICE_NUM] [VISIABLE_DEVICES(0,1,2,3,4,5,6,7)] [DATASET_PATH]
### Launch
```
# training example
Ascend: sh run_train.sh Ascend 8 192.168.0.1 0,1,2,3,4,5,6,7 ~/imagenet/train/
GPU: sh run_train.sh GPU 8 0,1,2,3,4,5,6,7 ~/imagenet/train/
```
### Result
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.
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](https://arxiv.org/pdf/1905.02244) 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.
# Model architecture
The overall network architecture of MobileNetV3 is show below:
- 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
# Environment Requirements
- 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.
- Ascend: sh run_train.sh Ascend [DEVICE_NUM] [SERVER_IP(x.x.x.x)] [VISIABLE_DEVICES(0,1,2,3,4,5,6,7)] [DATASET_PATH]
- GPU: sh run_trian.sh GPU [DEVICE_NUM] [VISIABLE_DEVICES(0,1,2,3,4,5,6,7)] [DATASET_PATH]
### Launch
```
# training example
Ascend: sh run_train.sh Ascend 8 192.168.0.1 0,1,2,3,4,5,6,7 ~/imagenet/train/
GPU: sh run_train.sh GPU 8 0,1,2,3,4,5,6,7 ~/imagenet/train/
```
### Result
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.
