TransUNet
TransUNet copied to clipboard
This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.
i use the same paramater like SGD, lr for ACDC. but the loss can not be reduced when loss = 0.2 Please tell me what are your training parameters?
please use wget https://storage.googleapis.com/vit_models/imagenet21k/R50+ViT-B_16.npz to get the correct pretrained model.
Acdc
This branch contains the code to prepare ACDC dataset for training with TransUNet. Modified train and test scripts are also provided.
Hello, your article is very well written! Could you please send me your processed ACDC dataset? My email is [email protected], if you can help, I will be very grateful! Thank...
I want to train my own dataset. So in the image preprocessing, as long as the size of the input image is 224*224 and the input of the model is...
Hi, Great Work!!! Can you please tell me the reason behind [-125, 275], since I am also working on MRI images, that why just wondering why you chose this specific...
Thanks for the good code, bro! Currently, this code only works with equal size (width equals height). Can you help me how to adapt the network to work with different...
Hello, I sent an email to you to get the preprocessed database, but maybe because you are too busy to check your mailbox or my email is judged as spam,...