# SE-ResNet

**Repository Path**: l_emon/SE-ResNet

## Basic Information

- **Project Name**: SE-ResNet
- **Description**: No description available
- **Primary Language**: Python
- **License**: AFL-3.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2021-02-17
- **Last Updated**: 2021-11-03

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Training Process
## Usage
### running on Ascend
```bash
# distributed training
Usage: 
sh run_distribute_train.sh se-resnet50 imagenet2012 [RANK_TABLE_FILE] [DATASET_PATH]

# standalone training
Usage: 
export DEVICE_ID=[0|1|2|3|4|5|6|7]
python train.py --net=se-resnet50  --dataset=[cifar10|imagenet2012]  --dataset_path=[DATASET_PATH]

# run evaluation example
Usage:
export DEVICE_ID=[0|1|2|3|4|5|6|7]
python eval.py --net=se-resnet50 --dataset=[cifar10|imagenet2012] --checkpoint_path=[CHECKPOINT_PATH] --dataset_path=[DATASET_PATH]

```

# Result

- Evaluating SE-ResNet50 with ImageNet2012 dataset

```bash
result: {'top_1_accuracy': 0.7771423969072165, 'top_5_accuracy': 0.9385067654639175} ckpt=train_parallel0/resnet-90_1251.ckpt
```

- Evaluating SE-ResNet50 with cifar10 dataset

```bash
result: {'top_5_accuracy': 0.9987980769230769, 'top_1_accuracy': 0.9489182692307693} ckpt=resnet-90_1562.ckpt
```