MedSegDiff

MedSegDiff copied to clipboard

help! run the model on my own dataset, visdom show nothing. and have this erro: WARNING:root:Setting up a new session... [W socket.cpp:697] [c10d] The client socket has failed to connect to [DESKTOP-BP72V]:55472 (system error: 10049 - �����������У�������ĵ�ַ��Ч��).

1

WARNING:root:Setting up a new session... [W socket.cpp:697] [c10d] The client socket has failed to connect to [DESKTOP-BP72V]:55472 (system error: 10049 - �����������У�������ĵ�ַ��Ч��). when i run the model on my own...

fayeGou

I want to know which part of the code the image size is in

1

I want to know which part of the code the image size is in. image_size is 256, but the image size in the downloaded ISCI data set is 1022*767. Where...

sonnystalin

Where is the code of SS-former

3

22/5000 Where exactly is the code of SS-former embodied

Yutong0429Hou

some question about V1 version

2

First of all, I want to express my sincere gratitude for your remarkable work. I am particularly interested in the dynamic conditional encoding and FF-parser mentioned in your V1 version....

tensorctn

How long will you use to train the model?

3

How long will you use to train the model? I use single RTX3080Ti and it have taken about 4 days for 100k iterations ,but the training model keeps running.

sonnystalin

which .pt should I use to sample?

4

There are three types of parameter files after training， which should I ues to sample? ![Uploading 微信图片_20240604160724.png…]()

take-off-xyz

Do you have any trained model weights that you can share?

1

deffso

Question about the wrong output when trying BraTS20 in MedSegDiff V2 code

4

I have tried to run the given script following instructions on MICCAI_BraTS2020_TrainingData but get a segmentation of the whole brain rather than the ground truth tumor. The first image is...

Mark-bit3

What are these losses calculated separately

1

 Hello, I have run train.py, but I don't quite understand the meaning of these losses respectively, and why there are so many losses, it seems that there are not...

QijingGJ

Command used: `python scripts/segmentation_train.py --version 1 --data_name ISIC --data_dir $train_data_dir --out_dir $train_output_dir --image_size 256 --num_channels 128 --class_cond False --num_res_blocks 2 --num_heads 1 --learn_sigma True --use_scale_shift_norm False --attention_resolutions 16 --diffusion_steps 1000...

pedropesserl