search

himashi92 / vizviva_brats_2021

[Brainlesion 2021] Official PyTorch Implementation for Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task
MIT License
20 stars 3 forks source link

Pretrained Model #1

Closed KarikalStrom closed 2 years ago

KarikalStrom commented 2 years ago

Hello, first of all, great job. I am trying to use this model and implement it in an app I'm working on. I can't find the pre-trained model if you didn't share it yet is there anyway you can share it with me. My computer isn't strong enough to run the training. Thanks in advance.

himashi92 commented 2 years ago

Hi, you can find the pretrained model here https://drive.google.com/file/d/11YmBPePPmnqE9W40ZqschovmiPx6lZ-2/view?usp=sharing

thisisatharva commented 2 years ago

Hey, I was trying to load these pretrained weights using

model_maker = getattr(model, 'unet') model_1 = model_maker.Unet( 4, 3, width=24, norm_layer=get_norm_layer('inorm'), dropout=0.) model_2 = model.unet.Unet(4, 3, width=32, norm_layer=get_norm_layer('inorm'), dropout=0.) checkpoint = torch.load('../model_best.pth.tar') model_1.load_state_dict(checkpoint['state_dict'])

But I am getting a shape mismatch error. Any reason why this is happening, I followed the code from test.py.