making decoder dataloaders something wrong

[LearningJack]

Could you help me? I had run the clip-retrieval and then generate the embedding.npy.But when I run the reorder-embeddings, it occured invalid literal for int() with base 10: 'img_test/COCO_train2014_000000581909'. How can I solve this problem?

[rom1504]

You need to download using webdataset format when using img2dataset

…

On Mon, May 23, 2022, 14:36 LearningJack ***@***.***> wrote: [image: issue] <https://user-images.githubusercontent.com/38984606/169820565-180a04d3-4f88-4ff6-83df-07d03838a208.jpg> Could you help me? I had run the *clip-retrieval* and then generate the embedding.npy.But when I run the *reorder-embeddings*, it occured *invalid literal for int() with base 10: 'img_test/COCO_train2014_000000581909'*. How can I solve this problem? — Reply to this email directly, view it on GitHub <#110>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAR437U6UNXLP3HIBPDYWKLVLN3V3ANCNFSM5WVWRWBQ> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[LearningJack]

But when I have my own dataset, how can I resolve this issue?

[rom1504]

Same solution, you use webdataset format

…

On Mon, May 23, 2022, 14:57 LearningJack ***@***.***> wrote: But when I have my own dataset, how can I resolve this issue? — Reply to this email directly, view it on GitHub <#110 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAR437VTZDTO3IJ5YBCEXTTVLN6D7ANCNFSM5WVWRWBQ> . You are receiving this because you commented.Message ID: ***@***.***>