Closed MaroonAmor closed 2 years ago
Hi, add --arch ViTB16
to the command in the readme to use ViTB16 instead of ResNet50.
by default we use the same learning rate for the last layer as rest of the model, to do this, pass --fc_lr_mul 0
@yash0307 Thanks for the reply. I did use the same parameters for training as you replied.
FYI, in my experiment, the model with ViTB16 after training 55 epochs achieved Recall@1 of 88.3% on the SOP dataset, which is even higher than the one reported in the paper. Thanks again for the great work!
@MaroonAmor, good to know. Thank you for your interest in our work.
Hi @yash0307,
Thanks a lot for sharing your work.
Could you also share the command line of how to run an experiment on the SOP dataset using the
"ViTB16"
backbone?It seems that the
src/main.py
file does not support the"ViTB16"
backbone. Also, the code cannot run through the linefc_params = model.model.last_linear.parameters()
with the default parameterfc_lr_mul
. Thetorch.optim.AdamW
optimizer is not supported for the"ViTB16"
backbone.Thanks again.