You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
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~.
The text was updated successfully, but these errors were encountered:
irsLu
changed the title
There is an error when I run the speed_test.py
Question about running the speed_test.py
Nov 9, 2022
Hi~
![image](https://user-images.githubusercontent.com/42465965/200749518-68c771f7-d98c-4d4c-abdd-c08fc879eb78.png)
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~.
The text was updated successfully, but these errors were encountered: