mindspore/example/mobilenetv2_quant

• MobileNetV2 Description
• Model architecture
• Dataset
• Features
• Environment Requirements
• Script description
• • Script and sample code
  • Training process
  • • Usage
    • Launch
    • Result
  • Eval process
  • • Usage
    • Launch
    • Result
• Model description
• • Performance
  • • Training Performance
    • • Inference Performance
• ModelZoo Homepage

MobileNetV2 Description

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 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:

Link

Dataset

Dataset used: imagenet

• 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)
  • Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the application form to ascend@huawei.com. Once approved, you can get the resources.
• Framework
  • MindSpore
• For more information, please check the resources below：
  • MindSpore tutorials
  • MindSpore API

Script description

Script and sample code

├── MobileNetV2        
  ├── Readme.md                      
  ├── scripts 
  │   ├──run_train.sh                  
  │   ├──run_eval.sh                    
  ├── src                              
  │   ├──config.py                     
  │   ├──dataset.py
  │   ├──luanch.py       
  │   ├──lr_generator.py                                 
  │   ├──mobilenetV2.py
  ├── train.py
  ├── eval.py

Training process

Usage

• 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] [CKPT_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/

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.

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

Eval process

Usage

• Ascend: sh run_infer.sh Ascend [DATASET_PATH] [CHECKPOINT_PATH]

Launch

# infer example
    Ascend: sh run_infer.sh Ascend ~/imagenet/val/ ~/train/mobilenet-200_625.ckpt

checkpoint can be produced in training process.

Result

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

Model description

Performance

Training Performance

Parameters	MobilenetV2	MobilenetV2 Quant
Resource	Ascend 910 cpu:2.60GHz 56cores memory:314G	Ascend 910 cpu:2.60GHz 56cores memory:314G
uploaded Date	05/06/2020	06/12/2020
MindSpore Version	0.3.0	0.3.0
Dataset	ImageNet	ImageNet
Training Parameters	src/config.py	src/config.py
Optimizer	Momentum	Momentum
Loss Function	CrossEntropyWithLabelSmooth	CrossEntropyWithLabelSmooth
Loss	200 epoch:1.913	50 epoch:1.912
Train Accuracy	ACC1[77.09%] ACC5[92.57%]	ACC1[77.09%] ACC5[92.57%]
Eval Accuracy	ACC1[77.09%] ACC5[92.57%]	ACC1[77.09%] ACC5[92.57%]
Total time	48h	12h
Checkpoint	/	mobilenetv2.ckpt

Inference Performance

Parameters	Ascend 910	Ascend 310	Nvidia V100
uploaded Date	06/12/2020
MindSpore Version	0.3.0
Dataset	ImageNet, 1.2W
batch_size
outputs
Accuracy
Speed
Total time
Model for inference

ModelZoo Homepage

Link