We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
keras-ctpn/ctpn/layers/target.py
Line 204 in 22bdee3
ctpn_target_graph
tf.float32
tf.int64
The text was updated successfully, but these errors were encountered:
@RabbearSu 这个代码已经注释了哦
Sorry, something went wrong.
@yizt 我看您在tf_utils.py里备注说尽量用原生的tf.map_fn,效率更高
tf_utils.py
tf.map_fn
@RabbearSu 一般情况下用tf.map_fn是更好一些,我这里加了自定义度量后,还用tf.map_fn遇到了bug,没有解决;所以还是改为用batch_slice了。
@yizt 原来是这样,我尝试一下能不能改成tf.map_fn
No branches or pull requests
keras-ctpn/ctpn/layers/target.py
Line 204 in 22bdee3
在前面
ctpn_target_graph
的输出中,后三个度量的类型均为tf.float32
,可是这里倒数第四个指定类型为tf.int64
,是否应为tf.float32
呢?The text was updated successfully, but these errors were encountered: