对于以下图片应该怎么训练检测模型好
#16095
Replies: 3 comments 2 replies
-
|
您好，两种方式应该都不影响模型收敛，不过第二种看起来标注成本更低，而且点数和花色距离比较近，模型更倾向于将距离较近的文字连接在一起 |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
请问标注的时候需要留意仅仅框选纸牌里面内容吗，如图1 |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
这个和您识别阶段的训练数据有关吧，应该都不影响。图1则按图1的方式裁剪出来训练，图2则按图2裁剪出来训练。 |
Beta Was this translation helpful? Give feedback.
-
|
顶一下 |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
你自己先试试看 |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
对于以下图片，我想识别出点数和花色，必然是要对检测模型做训练对吧，那么我应该如何做训练效果是比较好的请问
图1还是图2的方式呢？
Beta Was this translation helpful? Give feedback.
All reactions