未验证 提交 1f5b8d5c 编写于 作者: W wangguanzhong 提交者: GitHub

refine fruit doc (#16)

上级 7aa11973
......@@ -26,7 +26,7 @@ Training:
python -u tools/train.py -c configs/yolov3_mobilenet_v1_fruit.yml \
--use_tb=True \
--tb_log_dir=tb_fruit_dir/scalar \
--eval \
--eval
```
Use `yolov3_mobilenet_v1` to fine-tune the model from COCO dataset. Meanwhile, loss and mAP can be observed on tensorboard.
......
......@@ -26,7 +26,7 @@ export CUDA_VISIBLE_DEVICES=0
python -u tools/train.py -c configs/yolov3_mobilenet_v1_fruit.yml \
--use_tb=True \
--tb_log_dir=tb_fruit_dir/scalar \
--eval \
--eval
```
训练使用`yolov3_mobilenet_v1`基于COCO数据集训练好的模型进行finetune。训练期间可以通过tensorboard实时观察loss和精度值,启动命令如下:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册