Medical-SAM-Adapter

Medical-SAM-Adapter copied to clipboard

Traceback (most recent call last): File "train.py", line 27, in from dataset import * File "D:\pycharmprogram\Medical-SAM-Adapter-main\dataset.py", line 19, in from utils import random_click File "D:\pycharmprogram\Medical-SAM-Adapter-main\utils.py", line 57, in from models.discriminator...

yasaorder

This error happens during validation of ISIC dataset, and it disallows further training. Can you please advise? @WuJunde

AmrinKareem

Hi @WuJunde could you please include information about the number of epochs you trained the model on both datasets. The number of epochs in the global settings is set to...

AmrinKareem

Training stuck after loading 3d data

4

Training stuck after loading 3d data  python train.py -net sam -mod sam_adpt -exp_name msa-3d-sam-btcv -sam_ckpt ./sam_vit_b_01ec64.pth -image_size 1024 -b 1 -dataset decathlon -thd True -chunk 1 -data_path /mnt/data/abdomen -num_sample...

CarinaL99

Text prompt

2

Hi, thanks for sharing. I haven't seen any code for the text prompts. Did I miss something or just you haven't release? thanks!

taipingeric

what I use is RTX 3090 (24G), which is far from enough.

zutsusemi

actual shape : img : torch.Size([64, 256, 256, 3]) pred_mask : torch.Size([64, 1, 256, 256]) gt_mask; torch.Size([64, 1, 256, 256]) vis code shape : img : torch.Size([4, 256, 256, 256])...

krishnaadithya

Hi, thank you for the great work! I trained the MedSAM-adapter on 2D 256x256 CT images obtained from Kidney Tumor Segmentation (KiTS) dataset for 50 epoches, the best model is...

mlszy928

Thanks！ Your paper mentions about the optimization of the click strategy ,mainly is,distinction the first click and performing iterative clicks. I think that’s cool idea will definitely help me greatly...

xiawei20161308104

 When I get this error, I think it is caused by this object not being able to use the middle brackets. So I changed the following source code： before：...

nanshanvv