Closed LearningJack closed 2 years ago
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?
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 https://github.com/lucidrains/DALLE2-pytorch/issues/110, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAR437U6UNXLP3HIBPDYWKLVLN3V3ANCNFSM5WVWRWBQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>
But when I have my own dataset, how can I resolve this issue?
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 https://github.com/lucidrains/DALLE2-pytorch/issues/110#issuecomment-1134643806, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAR437VTZDTO3IJ5YBCEXTTVLN6D7ANCNFSM5WVWRWBQ . You are receiving this because you commented.Message ID: @.***>