Closed gowriaddepalli closed 4 years ago
Thanks for your observation, but I cannot find the specific code fragment you're referring to. Can you point to the lines via URLs? See https://docs.github.com/en/github/managing-your-work-on-github/creating-a-permanent-link-to-a-code-snippet
Thanks for your interest in our work!
Actually, the image_id
includes .jpg
. For example, the score map is located at {output_path}/image1.jpg.npy
.
yes, but as per documentation is was just {output_path}/image1.npy
Apart from that, if you do that, as well, i start getting KeyError: 'image.jpg' in this self.mask_paths[image_id],
any suggestions why is it giving this error, when everything is done as per the metadata/localization.txt
I managed to clear the above error. Thanks for your time.
The code in the data loader reads the image_ids file as: which has.jpg appended
with open(metadata['image_ids' + suffix]) as f: for line in f.readlines(): image_ids.append(line.strip('\n'))
but while reading open Images data, and reading the localization.txt, it expects. path_file.jpg.npy. isnt it wrong? should it not be path_file.npy. The jpg should be dropped. It would be great if you could clear this issue.