-
Hi, the Pre-exacted Image Features and Pre-trained Models is not able to download from the provided link
```bash
/path/to/azcopy copy https://biglmdiag.blob.core.windows.net/vinvl/image_features/c…
-
Ran out of input
File "/nfs/tangt/anaconda3/envs/VinVL/lib/python3.8/site-packages/torch/serialization.py", line 764, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
…
-
Hi, after inserting the object into the background image, how can I generate the pred.final_result_test_0.tsv from these images. And how can I match the pred with the test?
-
Hello there,
Thank you so much for this great repository. I've been using VinVL for a while now and I'm really pleased with its accuracy. However, considering its size, I was wondering whether you …
-
I ran the following command (from the [README](https://github.com/microsoft/scene_graph_benchmark#vinvl-feature-extraction)):
```
python tools/test_sg_net.py --config-file sgg_configs/vgattr/vinvl…
-
Hello,
I got the error message Segmentation fault (core dumped) all the time when I am trying to run the ITA model for all three datasets.
Here are the full log messages:
CUDA_VISIBLE_DEVICES=0…
-
I am using the given SAS token to extract this YAML file
> coco_flickr30k_googlecc_gqa_sbu_oi_x152c4big2exp168.yaml
`./azcopy copy "https://biglmdiag.blob.core.windows.net/vinvl/pretrain_corpu…
-
Hello!
I have a question about extracting region features for image captioning:
- in VinVL paper, it states that 2048 region features are stacked with 6 positionally encoded features (bbox, its h…
-
Hello~
Thanks for uploading VinVL feature for NoCaps validation images.
To generate results on test set, VinVL features for NoCaps test images are needed. Would you mind releasing VinVL features for…
-
Hi. Thanks in advance.
The following command to download a VinVL model fails
~/azcopy/azcopy copy 'https://biglmdiag.blob.core.windows.net/vinvl/model_ckpts/coco_caption' vinVL_models_coco --rec…