AarohiSingla / Image-Classification-Using-Vision-transformer

Image Classification Using Vision transformer from Scractch
55 stars 37 forks source link

Problem with different image size #1

Open shuvo14051 opened 1 year ago

shuvo14051 commented 1 year ago

from torchinfo import summary

summary(model=pretrained_vit, input_size=(32, 3, 128, 128), col_names = ['input_size', 'output_size', 'num_params', 'trainable'], col_width = 20, row_settings = ['var_names'])

I have images of shape 128,128 And for this, the code is not working. Can you please tell me why?

umaiskhan42 commented 9 months ago

Can you share your code here so i can view what is the problem exactly.