Medical-Transformer icon indicating copy to clipboard operation
Medical-Transformer copied to clipboard

Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" - MICCAI 2021

Results 36 Medical-Transformer issues
Sort by recently updated
recently updated
newest added

Traceback (most recent call last): File "train.py", line 140, in output = model(X_batch) File "/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axialnet.py", line 507, in forward return self._forward_impl(x)...

I used GLAS dataset,but my training results are black,I think it's may be caused by the dataset. So I want to know how should I prepare the dataset or how...

when I run this command: python train.py --train_dataset "Traindata" --val_dataset "Traindata" --direc 'result' --batch_size 4 --epoch 400 --save_freq 10 --modelname "gatedaxialunet" --learning_rate 0.001 --imgsize 128 --gray "no", then an error...

When reproducing the code, using the "Medt" network, you have not encountered the training and test results of the situation is very different

i found that the output tensor are =0.5] = 1 ,tmp[tmp

Hi jeya-maria-jose!👋, I added this optional feature to digitally sign you source-code and track it on a blockchain node should you ever be audited or experience a software supply-chain attack....

Hi, I have a ground-truth with 3 classes including background with values 0,127,255. As mentioned in #43 I changed num_classes=3 in axialnet.py In utils.py, https://github.com/jeya-maria-jose/Medical-Transformer/blob/703a080d66d16673be1b8770bca143956c9f0e8a/utils.py#L156-L157 which makes the ground-truth with...

My training results are quite different from yours. I think it may be a problem of data processing. My email is [email protected] Thank you very much.

while testing model i'm getting error : aug = args.aug AttributeError: 'Namespace' object has no attribute 'aug' can you please help me with this query

Is the Input size must be 128*128