gsrivas4

@brightbsit @benob I was able to run Oscar with pytorch version 1.7.0+cu101 and latest apex master.

@benob I have used the master branch of apex - https://github.com/NVIDIA/apex.git. However, I was able to run oscar code only on a single GPU machine. I had some issues running...

@KrystalCWT I am also getting random captions, as yours, when I run the checkpoint, checkpoint-29-66420, on coco captions Karpathy test split images. However, when I fine-tune the checkpoint using following...

@shekarneo If you had still not figured out, the answer is here - https://github.com/clovaai/CRAFT-pytorch/issues/7#issuecomment-508605897.

@ckzbullbullet @pzzhang Were you able to solve the issue. I am getting similar error when I try to download the models given here - https://github.com/pzzhang/VinVL/blob/main/DOWNLOAD.md#pre-trained-models ``` azcopy copy https://penzhanwu2.blob.core.windows.net/results/vinvl/od_models/vinvl_vg_x152c4.pth ....

My issue was resolved using the latest links provided on the repo. I had to use https://penzhanwu2.blob.core.windows.net/sgg/sgg_benchmark/vinvl_model_zoo/vinvl_vg_x152c4.pth instead of the old link https://penzhanwu2.blob.core.windows.net/results/vinvl/od_models/vinvl_vg_x152c4.pth. This resolved the error.