Question about running the speed_test.py

[irsLu]

Hi~
I want to run the speed_test.py, but there is an error as follow:
q, k, v = qkv.view(B, N, self.num_heads,
shape '[2048, 50176, 4, -1]' is invalid for input of size 308281344
when I check the code, I find that the code remove batchnorm of model, and the patch_embed of model is also removed. Therefore, the transformer blocks can not reshape the input.

My question is how I fix this problem?
And When I delete this line of removing batchnorm, I find the result of 'levit.LeViT_128S, 2048, 224' is 20761 images/s on RTX 3090 which is a lot higher than what you reported (12880 images/s reported in Tab 3). Is this result reasonable?
I am looking forward to your reply, thx~.

[btgraham]

Hello. What is your torch.__version__ please?

[irsLu]

Hello. What is your torch.__version__ please?

I'm so sorry~, I find it is my fault. I'm sorry to bother you. And good luck with your research

[btgraham]

No problem. Thanks for your interest.