Why validating model without taking "with torch.no_grad()"?

[libo-huang]

Thanks for your valuable project.

Below I found that you take with torch.no_grad(): on the dataset (i.e., input and target in lines 210-211) rather than on the model in line 213.
As shown in Evaluating pytorch models: with torch.no_grad vs model.eval() and
‘model.eval()’ vs ‘with torch.no_grad()’, it will take too much memory. But I am not sure about taking no with torch.no_grad block on line 213 whether influences the model's outputs.

AlwaysBeDreaming-DFCIL/learners/default.py

Lines 206 to 226 in 50d9c2e

	for i, (input, target, task) in enumerate(dataloader):
	if self.gpu:
	with torch.no_grad():
	input = input.cuda()
	target = target.cuda()
	if task_in is None:
	output = model.forward(input)[:, :self.valid_out_dim]
	acc = accumulate_acc(output, target, task, acc, topk=(self.top_k,))
	else:
	mask = target >= task_in[0]
	mask_ind = mask.nonzero().view(-1)
	input, target = input[mask_ind], target[mask_ind]
	mask = target < task_in[-1]
	mask_ind = mask.nonzero().view(-1)
	input, target = input[mask_ind], target[mask_ind]
	if len(target) > 1:
	output = model.forward(input)[:, task_in]
	acc = accumulate_acc(output, target-task_in[0], task, acc, topk=(self.top_k,))