Question about example notebook
repoholder23 opened this issue · comments
repoholder23 commented
Hi, I have a question about the example notebook: is the ViT model pretrained or do we start training from scratch?
In case we start training from scratch, is there a way we can start with a pretrained model instead? Thanks!
Argos Open Tech commented
The example notebook is training the model from scratch here:
for data, label in tqdm(train_loader):
data = data.to(device)
label = label.to(device)
output = model(data)
loss = criterion(output, label)
optimizer.zero_grad()
loss.backward()
optimizer.step()