Error on single image inference, thanks about tanet HOT 7 OPEN

My current workaround solution is to use multiple images in a batch. However, it might be better to figure out how to solve the single image issue.

In addition, the model produces a softmax output with 10 element for a single image, because I am using the AVA model. How can we compute a single score for an image? Thank you.

from tanet.

1. I have never encountered such a problem before ，you may refine the function of "validate(opt, model=model, loader=dataloader_test……" when bs=1，to see if you can solve this problem，see issue 8.
2. use the function of "def get_score(opt, y_pred)" in my code to obtain a score.

from tanet.

1. I have never encountered such a problem before ，you may refine the function of "validate(opt, model=model, loader=dataloader_test……" when bs=1，to see if you can solve this problem，see issue 8.

   2. use the function of "def get_score(opt, y_pred)" in my code to obtain a score.

I got it, thanks a lot.

from tanet.

@junyongyou hi could you solve this issue without using the dataloader? For now I am doing

bn7 = nn.BatchNorm1d(q.shape[0])
bn7.eval()

because it seems that the problem is that the BatchNorm1d is in training mode, although we set the whole model to eval. I am sure there is nicer solution. I guess the BatchNorm should be created when creating the TargetNet and then the forward pass just calls it.

from tanet.

@woshidandan Ok my solution doesn't work because it throws some wrong predictions. I would need the single image inference without dataloader for converting the model to onnx. Any ideas?

from tanet.

There are some sub-models that are not in eval mode even the whole model is set to eval. Thus, I don't know how to solve the problem.

from tanet.

@junyongyou 关于single image inference，想问下你这边解决了吗？

from tanet.