mirror of https://github.com/alibaba/EasyCV.git
150 lines
3.6 KiB
Markdown
150 lines
3.6 KiB
Markdown
# yolox tutorial
|
|
|
|
## Data preparation
|
|
To download the dataset, please refer to [prepare_data.md](../prepare_data.md).
|
|
|
|
Yolox support both coco format and [PAI-Itag detection format](https://help.aliyun.com/document_detail/311173.html#title-y6p-ger-5l7),
|
|
|
|
### COCO format
|
|
To use coco data to train detection, you can refer to [configs/detection/yolox/yolox_s_8xb16_300e_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_s_8xb16_300e_coco.py) for more configuration details.
|
|
|
|
### PAI-Itag detection format
|
|
To use pai-itag detection format data to train detection, you can refer to [configs/detection/yolox/yolox_s_8xb16_300e_coco_pai.py](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_s_8xb16_300e_coco_pai.py) for more configuration details.
|
|
|
|
## Local & PAI-DSW
|
|
|
|
To use COCO format data, use config file `configs/detection/yolox/yolox_s_8xb16_300e_coco.py`
|
|
|
|
To use PAI-Itag format data, use config file `configs/detection/yolox/yolox_s_8xb16_300e_coco_pai.py`
|
|
|
|
|
|
### Train
|
|
**Single gpu:**
|
|
|
|
```shell
|
|
python tools/train.py \
|
|
${CONFIG_PATH} \
|
|
--work_dir ${WORK_DIR}
|
|
```
|
|
|
|
**Multi gpus:**
|
|
|
|
```shell
|
|
bash tools/dist_train.sh \
|
|
${NUM_GPUS} \
|
|
${CONFIG_PATH} \
|
|
--work_dir ${WORK_DIR}
|
|
```
|
|
|
|
<details>
|
|
<summary>Arguments</summary>
|
|
|
|
- `NUM_GPUS`: number of gpus
|
|
|
|
- `CONFIG_PATH`: the config file path of a detection method
|
|
|
|
- `WORK_DIR`: your path to save models and logs
|
|
|
|
</details>
|
|
|
|
**Examples:**
|
|
|
|
Edit `data_root`path in the `${CONFIG_PATH}` to your own data path.
|
|
|
|
```shell
|
|
GPUS=8
|
|
bash tools/dist_train.sh configs/detection/yolox/yolox_s_8xb16_300e_coco.py $GPUS
|
|
```
|
|
|
|
### Evaluation
|
|
|
|
**Single gpu:**
|
|
|
|
```shell
|
|
python tools/eval.py \
|
|
${CONFIG_PATH} \
|
|
${CHECKPOINT} \
|
|
--eval
|
|
```
|
|
|
|
**Multi gpus:**
|
|
|
|
```shell
|
|
bash tools/dist_test.sh \
|
|
${CONFIG_PATH} \
|
|
${NUM_GPUS} \
|
|
${CHECKPOINT} \
|
|
--eval
|
|
```
|
|
|
|
<details>
|
|
<summary>Arguments</summary>
|
|
|
|
- `CONFIG_PATH`: the config file path of a detection method
|
|
|
|
- `NUM_GPUS`: number of gpus
|
|
|
|
- `CHECKPOINT`: the checkpoint file named as epoch_*.pth.
|
|
|
|
</details>
|
|
|
|
**Examples:**
|
|
|
|
```shell
|
|
GPUS=8
|
|
bash tools/dist_test.sh configs/detection/yolox/yolox_s_8xb16_300e_coco.py $GPUS work_dirs/detection/yolox/epoch_300.pth --eval
|
|
```
|
|
|
|
### Export model
|
|
|
|
```shell
|
|
python tools/export.py \
|
|
${CONFIG_PATH} \
|
|
${CHECKPOINT} \
|
|
${EXPORT_PATH}
|
|
```
|
|
|
|
<details>
|
|
<summary>Arguments</summary>
|
|
|
|
- `CONFIG_PATH`: the config file path of a detection method
|
|
- `CHECKPOINT`:your checkpoint file of a detection method named as epoch_*.pth.
|
|
- `EXPORT_PATH`: your path to save export model
|
|
|
|
</details>
|
|
|
|
**Examples:**
|
|
|
|
```shell
|
|
python tools/export.py configs/detection/yolox/yolox_s_8xb16_300e_coco.py \
|
|
work_dirs/detection/yolox/epoch_300.pth \
|
|
work_dirs/detection/yolox/epoch_300_export.pth
|
|
```
|
|
|
|
### Inference
|
|
Download [test_image](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/data/small_coco_demo/val2017/000000017627.jpg)
|
|
|
|
```python
|
|
import cv2
|
|
from easycv.predictors import TorchYoloXPredictor
|
|
|
|
output_ckpt = 'work_dirs/detection/yolox/epoch_300.pth'
|
|
detector = TorchYoloXPredictor(output_ckpt)
|
|
|
|
img = cv2.imread('000000017627.jpg')
|
|
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
|
|
output = detector.predict([img])
|
|
print(output)
|
|
|
|
# visualize image
|
|
from matplotlib import pyplot as plt
|
|
image = img.copy()
|
|
for box, cls_name in zip(output[0]['detection_boxes'], output[0]['detection_class_names']):
|
|
# box is [x1,y1,x2,y2]
|
|
box = [int(b) for b in box]
|
|
image = cv2.rectangle(image, tuple(box[:2]), tuple(box[2:4]), (0,255,0), 2)
|
|
cv2.putText(image, cls_name, (box[0], box[1]-5), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 2)
|
|
plt.imshow(image)
|
|
plt.show()
|
|
```
|