./pretrained_pth/maxvit/maxvit_rmlp_small_rw_224_sw-6ef0ae4f.pth'

[ccncn]

what happen to this, the 2d code keep request this for training

[mrbird643]

what happen to this, the 2d code keep request this for training

Do you have a solution to this problem? Can you let me know?

[ccncn]

its a pretrained PTH file. just get it from the internet

[mrbird643]

its a pretrained PTH file. just get it from the internet

The link provided by the author in the 2D README section under "Model weights" regarding the "Learned weights" of the dataset Synapse, is it the weight data that he trained himself and is it used for testing purposes? Did you succeed in reproducing it? Why is my training process on the 2080 Ti with a 24GB dataset for Synapse very slow, even after changing the batch size?@ccncn

[bhupender-kaushal]

import timm
import torch

Download and load the pretrained model

model = timm.create_model('maxvit_rmlp_small_rw_224.sw_in1k', pretrained=True)
model.eval()

Save the model weights as a .pth file

torch.save(model.state_dict(), 'maxvit_rmlp_small_rw_224.sw_in1k.pth')

print("Model weights saved as maxvit_rmlp_small_rw_224.sw_in1k.pth") you can download the model from timm(≥0.9.0)and save it as whatever name you give, make sure the name given should reflect in your backbone loading.