hi all
M unable to find out why i should buffer freed error with below code
usig retain_Graph = true is expensive i cant use that option.
Please suggest where to retain the previous value and use that in running calculation for next iterations.
for idx, (imgs, labels) in enumerate(tk0):
imgs_train, labels_train = imgs.cuda(), labels.float().cuda()
output_train = model(imgs_train)
loss = criterion(output_train,labels_train)
if idx>=1:
loss=loss*0.3+0.7*prev_loss
with torch.no_grad():
prev_loss=loss
with amp.scale_loss(loss, optimizer) as scaled_loss:
scaled_loss.backward( )
optimizer.step()
optimizer.zero_grad()