Skip to content
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

训练part_A数据集,batch size=1,loss震荡很厉害,有什么解决办法吗 #83

Open
berylyellow opened this issue Sep 23, 2020 · 3 comments

Comments

@berylyellow
Copy link

No description provided.

@raisinglc
Copy link

把batch size调大
batch size = 1不就是online update,噪声肯定大

@winston-wen
Copy link

我冒昧揣测一下, 你用bsize=1是因为显存不够用吧? 如果是的话, 大胆一点, 把vgg层数和每层通道数降一降. 或许能顺便解决 loss震荡 的次生灾害.

@camerayuhang
Copy link

Setting the batch size to 1 is because the varying dimensions of input images. If all images had the same dimensions, we could increase the batch size. However, since the dimensions of the images are different, the batch size has to be set to 1. This is because we cannot stack images with different sizes into a single batch.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants