openmedlab / medfm Goto Github PK

File "C:\Anoconda\envs\pytorch\lib\site-packages\mmengine\config\config.py", line 1830, in call
key, val = kv.split('=', maxsplit=1)
ValueError: not enough values to unpack (expected 2, got 1)
['C:\master\configs\vit-b_vpt\1-shot_chest.py']

Hi there.

Thanks for sharing the code. I have a question about generate_few-shot_file.

For example, to get data /MedFMC/chest/images, I merged two folders from the raw dataset: MedFMC_train/chest/images/ and and MedFMC_val/chest/images/ . Did I do the right thing？

I run the preprocessing script as below:

python tools/generate_few-shot_file.py

However, I get "The validation set are not enough..." Is this normal？

I attach the output of generate_few-shot_file.py . Please correct me if I did something wrong

0 16
1 23
2 43
3 2
The validation set are not enough...
929 84 845
0 101
1 103
2 60
3 15
The validation set are not enough...
929 279 650
0 124
1 86
2 88
3 108
The validation set are not enough...
929 406 523
32 47
7 2018_83253_1-1_2019-02-20 18_38_45-lv1-2951-33576-3045-4336p0006.png
23 2019-07506-1-5-5_2019-05-29 06_09_14-lv1-14171-23920-4547-5510p0018.png
The validation set are not enough...
2358 30 2328
32 47
115 2019_03721_1-1_2019-02-20 19_49_57-lv1-10166-8058-6824-7989p0020.png
150 2019-07501-1-1-1_2019-05-29 08_22_25-lv1-9661-18329-4972-6041p0007.png
The validation set are not enough...
2358 265 2093
32 47
529 D201707788_2019-05-14 14_05_34-lv1-14456-57-11246-23473p0003.png
430 2019-07805-1-1-1_2019-05-29 05_23_08-lv1-28048-27815-6537-5899p0016.png
The validation set are not enough...
2358 959 1399
The validation set are not enough...
979 19 960
The validation set are not enough...
979 95 884
The validation set are not enough...
979 190 789

It seems that labels of all sample recorded in the test_WithLabel.txt of the ColonPath dataset are 0. Is this correct?

Hi, first of all thank you for the code. I would like to ask why my code is stuck for a long time before the training starts, is there anyone else who has the same problem as me?

Where can i find the datasets ? I don't find any instruction in this github to install the datasets.

Hello, thank you for the great work, really impressive. I am wondering if you tried the foundation model's performance on Cholec80 and CholecT45 ?
For example, including other cholecystectomy dataset during pretraining and test on Cholec80 and CholecT45.

Thanks, btw, is it possible to add you through the Wechat? My email address is [email protected]