未验证 提交 dbe9b77f 编写于 作者: J jerrywgz 提交者: GitHub

revise default data dir for inference in faster rcnn (#1636)

上级 16681794
......@@ -128,7 +128,7 @@ Inference is used to get prediction score or image features based on trained mod
python infer.py \
--dataset=coco2017 \
--pretrained_model=${path_to_pretrain_model} \
--image_path=data/COCO17/val2017/ \
--image_path=dataset/coco/val2017/ \
--image_name=000000000139.jpg \
--draw_threshold=0.6
......
......@@ -124,7 +124,7 @@ Faster RCNN 目标检测模型
python infer.py \
--dataset=coco2017 \
--pretrained_model=${path_to_pretrain_model} \
--image_path=data/COCO17/val2017/ \
--image_path=dataset/coco/val2017/ \
--image_name=000000000139.jpg \
--draw_threshold=0.6
......
......@@ -127,7 +127,7 @@ def parse_args():
add_arg('debug', bool, False, "Debug mode")
# SINGLE EVAL AND DRAW
add_arg('draw_threshold', float, 0.8, "Confidence threshold to draw bbox.")
add_arg('image_path', str, 'data/COCO17/val2017', "The image path used to inference and visualize.")
add_arg('image_path', str, 'dataset/coco/val2017', "The image path used to inference and visualize.")
add_arg('image_name', str, '', "The single image used to inference and visualize.")
# ce
parser.add_argument(
......
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