askerlee

Not sure what you mean by inference. test2d.py and test3d.py do inference on 2d and 3d datasets. Do you mean doing inference on a *single image* instead of a *dataset*?

Well it's easy 😁 (but a bit hacky) you can put the test images in a subfolder under the task data folder. Then add a dataset to test2d.py and set...

Did you put your own images in Kvasir-test? Looks like it's still because the number of classes is not set correctly. Have you tried to change this setting in test2d.py?

Seems I should provide a command line argument to allow overriding the hardcoded number of classes 🤔

This is weird... I need to download the dataset and check. But currently I'm busy with other work. Will come back to this issue later.

Hi @rezashaemi , you can download the preprocessed data from baidu netdisk: https://pan.baidu.com/s/1HAB5AMV8gqgoi5joUFdpVQ?pwd=5iud

Sorry for that. Could you pls try the dropbox link: https://www.dropbox.com/s/fd8hty3tgwwsl1i/refuge2020.tar?dl=0

hi @mahdiyehbakhshi822 , the preprocessed RIM data can be downloaded at: https://www.dropbox.com/s/8osan2fuon7nb0q/rim.zip?dl=0

@Lemonweier the two numbers in the filename are the (x,y) coordinates that each image is cropped at: https://github.com/askerlee/segtran/blob/master/code/MNet_DeepCDR/Step_1_Disc_Crop.py#L124

You can simply delete this condition. I'll fix it in the code base soon.