Oscar
Oscar copied to clipboard
microsoft
Oscar and VinVL
Where can I find object tag dictionary for OSCAR (vanilla) ? Is it the same one used in Faster-RCNN as OSCAR used faster RCNN features? Thanks
Is word embedding of object tags the same embedding matrix as word embedding of caption
Hello. I need to execute simple inference for Image-text retreival, I want a score for image and a caption, as presented [here for ViLT](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/ViLT/Using_ViLT_for_image_text_retrieval.ipynb). I've installed the package, and running...
Hi, Could I ask where to download the trainval_ans2label.pkl file? Also, I would like to try Oscar + VizWiz on the VizWiz dataset, how could I process the original annotation...
Hi Oscar Team, I read your superior paper some times and was interested in 'contrastive loss' mentioned in paper, but I can't find it in the source code. (1)Specifically ,I...
Hi :) First of all I want to thank you about developing and sharing such a great works. I wish you the best! I have a question about a part...
I have been playing with VinVL models for a while. I was trying to evaluate the model without the labels of the object detector. However after training the model with...
Hi guys, I am trying to generate my own features.tsv and labels.tsv for my dataset, but I am stuck at the following: 1. I have a slight confusion regarding what...
what is the "--model_name_or_path pretrained_models/base-vg-labels/ep_107_1192087"? I didn't fine such a file.
python oscar/run_retrieval.py \ --model_name_or_path vinvl/coco_ir/base/checkpoint-1340000 \ --do_train \ --do_lower_case \ --evaluate_during_training \ --num_captions_per_img_val 20 \ --eval_caption_index_file minival_caption_indexs_top20.pt \ --per_gpu_train_batch_size 16 \ --learning_rate 0.00002 \ --num_train_epochs 30 \ --weight_decay 0.05 \...
