Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,6 @@ tags:
|
|
| 5 |
- computer vision
|
| 6 |
- darknet
|
| 7 |
- yolo
|
| 8 |
-
- tensorflow
|
| 9 |
|
| 10 |
datasets:
|
| 11 |
- coco
|
|
@@ -163,12 +162,18 @@ python benchmarks.py --size 416 --model yolov4 --weights ./data/yolov4.weights
|
|
| 163 |
| YoloV4 FPS | | | |
|
| 164 |
|
| 165 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
# Transfer learning:
|
| 167 |
python train.py --weights ./data/yolov4.weights
|
| 168 |
```
|
| 169 |
The training performance is not fully reproduced yet, so I recommended to use Alex's [Darknet](https://github.com/AlexeyAB/darknet) to train your own data, then convert the .weights to tensorflow or tflite.
|
| 170 |
|
| 171 |
-
|
| 172 |
### References
|
| 173 |
|
| 174 |
* YOLOv4: Optimal Speed and Accuracy of Object Detection [YOLOv4](https://arxiv.org/abs/2004.10934).
|
|
|
|
| 5 |
- computer vision
|
| 6 |
- darknet
|
| 7 |
- yolo
|
|
|
|
| 8 |
|
| 9 |
datasets:
|
| 10 |
- coco
|
|
|
|
| 162 |
| YoloV4 FPS | | | |
|
| 163 |
|
| 164 |
|
| 165 |
+
### Traning your own model
|
| 166 |
+
```bash
|
| 167 |
+
# Prepare your dataset
|
| 168 |
+
# If you want to train from scratch:
|
| 169 |
+
In config.py set FISRT_STAGE_EPOCHS=0
|
| 170 |
+
# Run script:
|
| 171 |
+
python train.py
|
| 172 |
# Transfer learning:
|
| 173 |
python train.py --weights ./data/yolov4.weights
|
| 174 |
```
|
| 175 |
The training performance is not fully reproduced yet, so I recommended to use Alex's [Darknet](https://github.com/AlexeyAB/darknet) to train your own data, then convert the .weights to tensorflow or tflite.
|
| 176 |
|
|
|
|
| 177 |
### References
|
| 178 |
|
| 179 |
* YOLOv4: Optimal Speed and Accuracy of Object Detection [YOLOv4](https://arxiv.org/abs/2004.10934).
|