-
Notifications
You must be signed in to change notification settings - Fork 8
New issue
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
在resnet101的最后一个block的feature size和膨胀卷积问题 #2
Comments
@niujiaopeng @TreB1eN 你好,请问你跑通了吗?我出现了问题
请问怎么解决呢? |
应该是pytorch的版本问题,你用的是老版本? |
@TreB1eN 没哎,用的0.4.0 |
升级一下呢,我记得我遇到过这个问题,是版本的问题,你也可以google一下 |
hi, which CUDA and CUDNN version work fine for you? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
非常好的代码
我看了作者的tensorflow代码,问一个问题,是不是您这也是在标准的resnet101上修改的
普通的resnet的block4的feature size,也就是stage2的feature size应该是block3(rpn feature size)的二分之一,比如说提取rpn feature的size是50x75,那么最后进入那个head的应该是25x38,但是这里貌似最后的size还是50x75,block4和block3是一样的size,并且还用了2次膨胀卷积,这里的预训练参数是您完全按照这个网络结构重新在imagenet 上重新训练的呢,还是直接用标准的resnet的预训练参数?
The text was updated successfully, but these errors were encountered: