trinh-hoang-hiep

> I suggest you insert PDB or Print before line 138 of dataset/offline_dataset_crm_pad32.py to see if you can load the image manually. Thanks. I loaded img variable by image file.png...

> So, if you don't want to modify the dataset code, please change your dataset form. Or keep your dataset, and modify the code for loading seg.png. Thanks. Thank you...

 I try to test by using model_10000 and take seg by gray image but the result is so weird seg = Image.open(im[:-4]+'.png').convert('L') seg = self.resize_bi(crop_lambda(Image.open(im).convert('L')))

> detectron2-main I've seen it a lot in some issues, but I don't know what it is meaning of detectron2-main ?, what does it do?

> This is the download of detectron2 according to the readme of the entity network   I think this repo has 2 projects. one is entity, the other is...

> coarse mask I understood seg.png as raw mask of another segmentation neural network . So "High Quality Segmentation for Ultra High Resolution Images" is a post-processing right?

I have encountered the same problem recently. Have you solved it?Can you tell me your solution? Thank you! > @JohnGiorgi Just if you want to see that output I am...

Same problem, my server is too weak to handle 224x224 images