From 1f5b8d5c4c46ca52374723123268403d8f471008 Mon Sep 17 00:00:00 2001 From: wangguanzhong Date: Mon, 4 Nov 2019 11:48:56 +0800 Subject: [PATCH] refine fruit doc (#16) --- docs/QUICK_STARTED.md | 2 +- docs/QUICK_STARTED_cn.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/QUICK_STARTED.md b/docs/QUICK_STARTED.md index c6649f71f..926bdf39d 100644 --- a/docs/QUICK_STARTED.md +++ b/docs/QUICK_STARTED.md @@ -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. diff --git a/docs/QUICK_STARTED_cn.md b/docs/QUICK_STARTED_cn.md index 8c02ffb79..c11f041ba 100644 --- a/docs/QUICK_STARTED_cn.md +++ b/docs/QUICK_STARTED_cn.md @@ -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： -- GitLab