evalutils.exceptions.ValidationError: The images are not unique, please submit a unique image for each case.

Hello, I have encountered this error when submitting. Could anyone help me to check the certainty error?

These attempts were check: 1. Each cell has an instance id（max pixel value = cell number, background == 0） 2. Each segmentation map have at least one cell (not all 0 pixel value) 3. The compressed package does not contain other files (such as _MAXOSX) 4. Use the file save method as same as baseline 5. The shape of all samples is the same as the original image

1. Your folder contains a .DS_Store file
2. Please make sure each mask has at least five cells. assert np.max(mask)==len(np.unique(mask))-1 and np.max(mask)>5
3. Please use plt.imshow(mask) to visually check your mask.
4. The data type should be np.int16 (<65,000 cells) or np.int32 (>65,000 cells)

Thanks!

You can also use cross-validation to locally compute the F1 Score with the public evaluation code.

https://neurips22-cellseg.grand-challenge.org/metrics/