You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, thank you very much for your work!
I recently had some problems in reproducing this work. The address you provided for the dataset download, the data format is tsv and the code is reading in json format. Is it a direct conversion of tsv to a json format file, please?
When testing the model, I tried the demo, but it did not turn the "blue car" into a "red car", but I checked that it did load the model you provided, have you encountered such problems? Thank you very much!
The text was updated successfully, but these errors were encountered:
The original data format downloaded from the Conceptual Captions webpage contains the download link of each image and the meta information. It is not a direct transform from tsv to json. You need to download the images from Conceptual Captions dataset (or other datasets) first. The json file contains the filepath of each image.
I have updated a few bugs and typos in test.sh and test.py. Please try if you can run the demo now.
Hello, thank you very much for your work!
I recently had some problems in reproducing this work. The address you provided for the dataset download, the data format is tsv and the code is reading in json format. Is it a direct conversion of tsv to a json format file, please?
When testing the model, I tried the demo, but it did not turn the "blue car" into a "red car", but I checked that it did load the model you provided, have you encountered such problems? Thank you very much!
The text was updated successfully, but these errors were encountered: