forward_test output wrong

[manhtd98]

heree is my inference code. image shape is 6*3*800*1088 output only [(1,28,28), (1, 100), (1,4)] why i pass batch input with 6 samples but output only have 1 sample output model tenssort + gpu

[manhtd98]

I check the tensorrt wrapper and output of this function always have 1 sample output. Plz check the forward method of it

[lvhan028]

Hi, @manhtd98. Sorry for replying so late. Would you mind sharing your test code?

[manhtd98]

input_img shape is 6*3*800*1088

input_img = data["img"][0].contiguous()
 img_metas = data["img_metas"]
 outputs = self.model.forward_test(
 input_img, img_metas, return_loss=False, rescale=True)

But the output is only 1 images process

[lvhan028]

What's your command to convert the model? How do you prepare the input tensor?

[github-actions[bot]]

This issue is marked as stale because it has been marked as invalid or awaiting response for 7 days without any further response. It will be closed in 5 days if the stale label is not removed or if there is no further response.

[github-actions[bot]]

This issue is closed because it has been stale for 5 days. Please open a new issue if you have similar issues or you have any new updates now.