lwzhaojun

Have you encountered this problem? RuntimeError: CUDA out of memory. Tried to allocate 18.00 MiB (GPU 0; 8.00 GiB total capacity; 5.57 GiB already allocated; 10.05 MiB free; 607.43 MiB...

> I change metaLearner.py, line 174 like following: > ` torch.autograd.grad(loss, self.lstm2.parameters(), allow_unused=True, retain_graph=True)` > > It runs but Grads lstm + lstm2 print None . > Pricision goes up....

I also encountered this problem. Have you solved it?

Thank you. Let me try it.

Thank you for your answer. For example, when I use peoplenet, I set class-id=2, which means the class is face. But the detection box about the face is not displayed...

I seem to know. There are only cars and persons in your program, so my model peoplenet has no car, so there is no detection box for car. So if...

I changed the model to dashcamnet, the detection boxes about cars and persons will be displayed, and the statistical count of car flow is realized, but the flow of cars...