Closed ayush-angelium closed 4 years ago
Because your images in image-parse
are 24 bit RGB images, and the images in image-parse
in dataset are indexed images.
You should save the parsed images as indexed color image format or grayscale.
"Down to the latest detail" is better than cpvton model in terms of accuracy. That's I'm switching this model.
Hii @sergeywong , when I tested this model for custom images it gives an error, I have also implemented all the possible solution that mentioned in Issues like :
- I used im_h.permute in cp_dataset.py
- Installed different torchvision version(0.2.1).
- converted rgb to grey image for tensor resize.
- used different normalize in cp_dataset.py self.transform = transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5,), (0.5,))])
- manually resize in (1,256,192) but still facing tensor size issue.
Here are all possible outcomes that I applied when implementing this model. Please help me to solve this problem.
Hello, I also encountered this problem when testing the model for custom images. How did you solve it at last?
Hii @sergeywong , when I tested this model for custom images it gives an error, I have also implemented all the possible solution that mentioned in Issues like :
Here are all possible outcomes that I applied when implementing this model. Please help me to solve this problem.![Screenshot from 2020-06-25 20-36-46](https://user-images.githubusercontent.com/61581638/85748454-b49bbe00-b725-11ea-883e-0f383f75c00d.png)