Skip to content

M
models

PaddlePaddle / models
大约 1 年 前同步成功

通知 222
Star 6828
Fork 2962
M
models
未验证 提交 90c7255c 编写于 作者: L LielinJiang 提交者： GitHub
浏览文件
操作

Fix oom bug in image classification (#4372) 

* fix oom bug

* algin comment
上级 52ca7b75
显示空白变更内容
内联 并排
Showing with 1 addition and 1 deletion
PaddleCV/image_classification/utils/utility.py
浏览文件 @ 90c7255c
...@@ -131,7 +131,7 @@ def parse_args(): ...@@ -131,7 +131,7 @@ def parse_args():
add_arg('use_mixup', bool, False, "Whether to use mixup") add_arg('use_mixup', bool, False, "Whether to use mixup")
add_arg('mixup_alpha', float, 0.2, "The value of mixup_alpha") add_arg('mixup_alpha', float, 0.2, "The value of mixup_alpha")
add_arg('reader_thread', int, 8, "The number of multi thread reader") add_arg('reader_thread', int, 8, "The number of multi thread reader")
add_arg('reader_buf_size', int, 2048, "The buf size of multi thread reader") add_arg('reader_buf_size', int, 8, "The buf size of multi thread reader")
add_arg('interpolation', int, None, "The interpolation mode") add_arg('interpolation', int, None, "The interpolation mode")
add_arg('use_aa', bool, False, "Whether to use auto augment") add_arg('use_aa', bool, False, "Whether to use auto augment")
parser.add_argument('--image_mean', nargs='+', type=float, default=[0.485, 0.456, 0.406], help="The mean of input image data") parser.add_argument('--image_mean', nargs='+', type=float, default=[0.485, 0.456, 0.406], help="The mean of input image data")
......
Markdown is supported
0% 或 .
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 或