CUDA memory continuously increases when net(images) called in every iteration

8 
for i in xrange(100):
    out = net(input)
    loss += someLossFunction(input) # BAD, because it keeps continuing the graph over the for-loop

    loss = someLossFunction(input)   # this is fine

    loss = someLossFunction(input)
    total_loss += loss.data[0]              # this is fine
12 Likes