doc2graph

doc2graph copied to clipboard

RuntimeError: weight tensor should be defined either for all 4 classes or no classes but got weight tensor of shape: [3]

4

When I set train_batch_size=1, I got this error. It happen in ``` n_loss = compute_crossentropy_loss(n_scores.to(device), tg.ndata['label'].to(device)) ==> def compute_crossentropy_loss(scores: torch.Tensor, labels: torch.Tensor): w = class_weight.compute_class_weight(class_weight='balanced', classes=np.unique(labels.cpu().numpy()), y=labels.cpu().numpy()) return torch.nn.CrossEntropyLoss(weight=torch.tensor(w, dtype=torch.float32).to('cuda:0'))(scores,...

HonLZL

As the title says 👍 Curious what I need to change as I keep running into run-time errors: RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is...

0000F8

Pydantic problems with dependency mismatches

6

I get some conflicts where I can't run the main.py script. ``` ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour...

0000F8