提交 bf76aa7a 编写于 作者: Z zhengya01

update faster_rcnn

上级 66a75b98
......@@ -204,8 +204,6 @@ _C.pixel_means = [102.9801, 115.9465, 122.7717]
# clip box to prevent overflowing
_C.bbox_clip = np.log(1000. / 16.)
# ce
_C.enable_ce = False
# dataset path
_C.train_file_list = 'annotations/instances_train2017.json'
......
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