TransUNet

TransUNet copied to clipboard

Where is the CNN that they claim in the paper?

1

Karmush21

 I successfully ran the training file on Kaggle, but when running the test file, the error FileNotFoundError: [Errno 2] No such file or folder: '../model/TU_Synapse224/TU_pretrain_R50-ViT-B_16_skip3_bs24_224/epoch_29.pth. '. But my question...

ThaiBao107

The original code based on 3 channels,and the author copy the input images 3 times to fit the format,so you need to change somewhere to fit your dataset.But I think...

playpopi

Why are the training results different every time?为什么每次我的训练和测试结果不一样

congcongwy51

i am developing transunet architecture using tensorflow with and without resnet50 and no of parameters of Transunet code wth the Image_size=(224,224,3), embed_dim=512, MLP size= 3072, num_head=12, num_transformer_layer=12 is not 105...

Romita-ai

watertianyi

Hi, Thanks for this great job. I've met some error during training. All the parameters are default. After some iteration, the loss suddenly become large. Then came the NaN value....

nothingbut1

Synapse dataset

1

I didn't get a competent train result and I have some questions regarding it.  I think it's because the dataset is not made of purely abdominal images, but instead...

janet-rgb

train error: after a time, NaN or Inf found in input tensor.

3

Hello, executing python train.py --dataset owndataset --vit_name R50-ViT-B_16 --batch_size 12 --max_iterations 1000 --max_epochs 350 Any idea for the reasons for this? iteration 755 : loss : 0.232612, loss_ce: 0.031451 iteration...

andife