Replies: 1 comment 1 reply
-
@zj1010 this isn't a bug, it's a question for discussions, Looks like you're trying to input a '3D' tensor, the models here are setup for 2D so expect NCHW (batch, channels, height, width) tensors, depth is for 3D |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi, this project is excellent work! But i am kind of confused about how to set the model dimension.For example, when my data's config like [batchsize,channels,depth,height,width], and i try to use resnet50 for example, but the problem shows up: RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [4, 8, 14, 112, 112]. So are there any chances to set models' dimension? Maybe you already solve this problem but could you tell me how? I would be thankful if you could reply me soon.
Beta Was this translation helpful? Give feedback.
All reactions