Lesson 3 In-Class Discussion ✅

[go_go_gadget (Laura Langdon)]

Sorry to post this again, but I’m hoping someone will have an idea about what I might try to fix this. I’ve since found that if I restart the kernel and set the batch size to 1 (bs=1), I get a different error:

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 4096])

So that makes sense, and it shows that I’m successfully changing the batch size, but changing the batch size does not resolve the memory error.

Here’s my original post:

@go_go_gadget

Hi, I’m trying to run the planets notebook, and I’m getting a memory error when trying to find the learning rate. I tried reducing the batch size to 32 by running data = (src.transform(tfms, size=256).databunch(bs=32).normalize(imagenet_stats)) , but that didn’t work, so I also tried batch sizes of 16, 4, 2, and 1, always getting the same memory error. I’ve searched the forum and found others on this thread having the same problem, but changing the batch size seemed to work for them.

Am I changing the batch size incorrectly, or is there something else I should try?

Thanks for your insight!

I’d deeply appreciate any ideas!