mindspore/model_zoo/research/cv/ghostnet

• Contents
• • GhostNet Description
  • Model architecture
  • Dataset
  • Environment Requirements
  • Script description
  • • Script and sample code
  • Training process
  • Eval process
  • • Usage
    • Launch
    • Result
  • Model Description
  • • Performance
    • • Evaluation Performance
      • • GhostNet on ImageNet2012
        • • GhostNet on Oxford-IIIT Pet
          • Comparison with other methods on Oxford-IIIT Pet
  • Description of Random Situation
  • ModelZoo Homepage

Contents

• GhostNet Description
• Model Architecture
• Dataset
• Environment Requirements
• Script Description
  • Script and Sample Code
    • Training Process
    • Evaluation Process
      • Evaluation
• Model Description
  • Performance
    • Training Performance
    • Inference Performance
• Description of Random Situation
• ModelZoo Homepage

GhostNet Description

The GhostNet architecture is based on an Ghost module structure which generate more features from cheap operations. Based on a set of intrinsic feature maps, a series of cheap operations are applied to generate many ghost feature maps that could fully reveal information underlying intrinsic features.

Paper: Kai Han, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, Chang Xu. GhostNet: More Features from Cheap Operations. CVPR 2020.

Model architecture

The overall network architecture of GhostNet is show below:

Link

Dataset

Dataset used: Oxford-IIIT Pet

• Dataset size: 7049 colorful images in 1000 classes
  • Train: 3680 images
  • Test: 3369 images
• Data format: RGB images.
  • Note: Data will be processed in src/dataset.py

Environment Requirements

• Hardware（Ascend/GPU)
  • Prepare hardware environment with Ascend or GPU.
• Framework
  • MindSpore
• For more information, please check the resources below：
  • MindSpore Tutorials
  • MindSpore Python API

Script description

Script and sample code

├── GhostNet
  ├── Readme.md     # descriptions about ghostnet   # shell script for evaluation with CPU, GPU or Ascend
  ├── src
  │   ├──config.py      # parameter configuration
  │   ├──dataset.py     # creating dataset
  │   ├──launch.py      # start python script
  │   ├──lr_generator.py     # learning rate config
  │   ├──ghostnet.py      # GhostNet architecture
  │   ├──ghostnet600.py      # GhostNet-600M architecture
  ├── eval.py       # evaluation script
  ├── mindspore_hub_conf.py       # export model for hub

Training process

To Be Done

Eval process

Usage

After installing MindSpore via the official website, you can start evaluation as follows:

Launch

# infer example

  Ascend: python eval.py --model [ghostnet/ghostnet-600] --dataset_path ~/Pets/test.mindrecord --platform Ascend --checkpoint_path [CHECKPOINT_PATH]
  GPU: python eval.py --model [ghostnet/ghostnet-600] --dataset_path ~/Pets/test.mindrecord --platform GPU --checkpoint_path [CHECKPOINT_PATH]

checkpoint can be produced in training process.

Result

result: {'acc': 0.8113927500681385} ckpt= ./ghostnet_nose_1x_pets.ckpt
result: {'acc': 0.824475333878441} ckpt= ./ghostnet_1x_pets.ckpt
result: {'acc': 0.8691741618969746} ckpt= ./ghostnet600M_pets.ckpt

Model Description

Performance

Evaluation Performance

GhostNet on ImageNet2012

Parameters
Model Version	GhostNet	GhostNet-600
uploaded Date	09/08/2020 (month/day/year) ；	09/08/2020 (month/day/year)
MindSpore Version	0.6.0-alpha	0.6.0-alpha
Dataset	ImageNet2012	ImageNet2012
Parameters (M)	5.2	11.9
FLOPs (M)	142	591
Accuracy (Top1)	73.9	80.2

GhostNet on Oxford-IIIT Pet

Parameters
Model Version	GhostNet	GhostNet-600
uploaded Date	09/08/2020 (month/day/year) ；	09/08/2020 (month/day/year)
MindSpore Version	0.6.0-alpha	0.6.0-alpha
Dataset	Oxford-IIIT Pet	Oxford-IIIT Pet
Parameters (M)	3.9	10.6
FLOPs (M)	140	590
Accuracy (Top1)	82.4	86.9

Comparison with other methods on Oxford-IIIT Pet

Model	FLOPs (M)	Latency (ms)*	Accuracy (Top1)
MobileNetV2-1x	300	28.2	78.5
Ghost-1x w\o SE	138	19.1	81.1
Ghost-1x	140	25.3	82.4
Ghost-600	590	-	86.9

*The latency is measured on Huawei Kirin 990 chip under single-threaded mode with batch size 1.

Description of Random Situation

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

ModelZoo Homepage

Please check the official homepage.