Amr Mashlah
Amr Mashlah
@mike-chesnokov can I achieve the same results by setting item_biases to zeros like this: `model.item_biases = np.zeros_like(model.item_biases)` then use the LightFM predict method? `model.predict()`
I can confirm that `xformer` is the culprit here. I tried passing a list of generators using the new method described in PR #1718 but it didn't work `generator =...
NVIDIA 4090, Cuda is installed properly and was working fine before updating
I think it happens right after caching process, I tried now reducing "dataloader threads = 1" and got the same error: ``` NOTE: Using experimental fast data loading logic. To...
Tried a tiny sample dataset ~200 imgs it seem to have passed that error, it went through 100 epochs in under a minute, which is a bit suspicious, at the...
No I didn't, I just ran `install.sh`, seems like the script itself starts a venv
or downgrade your torchvision to `=0.14.1`