tacju / partimagenet Goto Github PK

The current files in the google drive link contains only the annotations.
Can you upload the images there as well?

What are the paths of the images which are showed in paper? Could you tell me that of the dog in Figure 1?

Thank you.

Thank you for the great work! May I ask when you plan on releasing the code for Compositor?

This is an excellent work! Using cocoapi (https://github.com/cocodataset/cocoapi), I can have this segmentation but not sure how to get the head of the ibex only.

Thanks for your excellent work! However, Is there something wrong in Line 18403 - Line 18422 of val.json? When I used coco.annToMask(ann) to visualize its mask, an error was reported.

Thank you for this work! Could you point me to the implementation of deeplab you used for your paper?

Hello again!

What is the meaning of each pixel label in the segmentation labels? They do not appear to match up with the 39 part labels and 10 whole labels. The json files also only contain the height and width of the image.

classes =[]
for i in tqdm(range(len(dataset_train))):
    image, whole_mask, part_mask = dataset_train[i]
    classes += np.unique(whole_mask).tolist()

c = Counter(classes)
print(c) # has counts for labels from 0 to 158

Could you please provide clarification?

How is the area being calculated in the annotations? Straightforward method is pixel counting but the area has 2 decimal places. Also pixel counting and the area in annotations are not matching.

Hello!

Do you describe what object categories you chose? For example, looking through the object annotations, it appears that dog gets mapped to multiple class values (e.g., 20, 48, 144). Does this refer to different breeds of dogs?

Hi! It is a very interesting work. When you release such dataset?

Are any of these images from the original ImageNet validation set, or are they all from the training set?

Thank you very much for sharing the datasets.

However, is the annotation "tier" in car and Bicycle should be "tire"?

When I convert an object segment into a semantic mask using coco API, I find some intersection areas between the different objects.
How should I solve the overleaping area when generating semantic mask labels?
Thanks for your reply.

I notice that each annotation has a field named 'category_id', the total number of all unique 'category_id' is 40, consistently in 'train.json' and 'test.json'. I wonder whether 'category_id' is the id of the object part, but it seems that the original paper does not mention it.