未验证 提交 2ba66200 编写于 作者: D Double_V 提交者: GitHub

Merge pull request #1496 from LDOUBLEV/dyg_db

adjust cls_batch_num to 6 for speed-up
......@@ -78,7 +78,7 @@ def parse_args():
parser.add_argument("--cls_model_dir", type=str)
parser.add_argument("--cls_image_shape", type=str, default="3, 48, 192")
parser.add_argument("--label_list", type=list, default=['0', '180'])
parser.add_argument("--cls_batch_num", type=int, default=30)
parser.add_argument("--cls_batch_num", type=int, default=6)
parser.add_argument("--cls_thresh", type=float, default=0.9)
parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
......
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