Method 1
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
Principle:
Cundnn follows the following criteria:
- if the dimension or type of network input data changes little, set torch.backends.cudnn.benchmark = true It can increase the operation efficiency; If the input data of the network changes every iteration, cndnn will find the optimal configuration every time, which will improve the operation efficiency ol>
Method 2
Tensor calculation should be written as follows:
train_loss += loss.item()