Giters
microsoft
/
Oscar
Oscar and VinVL
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1032
Watchers:
25
Issues:
201
Forks:
247
microsoft/Oscar Issues
Azcopy failed even with SAS token in the VinVL_DOWNLOAD.md file
Updated
3 months ago
Comments count
8
Azcopy failes with given SAS token
Updated
3 months ago
Comments count
1
"https://biglmdiag.blob.core.windows.net/vinvl/datasets/coco_caption" file does not download
Updated
5 months ago
Oscar fails with torch 2.1
Updated
6 months ago
Unable to run Oscar for Image Captioning
Updated
7 months ago
How to run captioning on any image? E.g. how to prepare the test.yaml and other required files required by the run_captioning.py?
Updated
7 months ago
Comments count
11
Public access for pretrained models are blocked
Closed
8 months ago
Comments count
5
The specified resource does not exist.
Updated
9 months ago
Comments count
5
VinVL features for datasets not available
Updated
9 months ago
Comments count
2
ModuleNotFoundError: No module named 'oscar'
Updated
a year ago
Comments count
1
How do you implement the multi-layer transformers?
Closed
a year ago
Comments count
1
Vocabulary of the test split
Updated
a year ago
what is checkpoint-29-66420
Updated
2 years ago
Comments count
2
Can you share the full NoCaps results on the test data?
Updated
2 years ago
Comments count
1
About checkpoint
Updated
2 years ago
How are the files in "train_logs/" and "test_logs/" encoded?
Updated
2 years ago
Comments count
1
coco-train-words.p
Closed
2 years ago
Comments count
2
missing "imageid2idx.json" when run script run_retrieval.py
Updated
2 years ago
Object tag dictionary for OSCAR (vanilla)
Updated
2 years ago
How to use Oscar / VinVL for image-text retreival inference?
Updated
2 years ago
Some doubt about contrastive loss and the output of BertImgForPreTraining
Updated
2 years ago
Comments count
1
Question about errors related to past tensor in modeling_bert.py
Updated
2 years ago
Comments count
1
train and validating without the label from object detection, (add_od_labels = False)
Updated
2 years ago
Comments count
1
yaml file unacceptable character
Closed
2 years ago
Comments count
1
Why do I need the test_caption.json file to generate caption
Closed
2 years ago
How can I fine-tune for the image-text retrieval task ?
Updated
2 years ago
The Num examples of COCO 1K and 5K test set
Closed
2 years ago
Comments count
1
Which object labels (tags) did you use for NoCaps challenge (VinVL + VIVO model)?
Updated
2 years ago
How to fine-tune retrieval task in another language?
Updated
2 years ago
Comments count
2
I can't train model using 2 GPUs
Updated
2 years ago
Comments count
4
File 'coco_flickr30k_googlecc_gqa_sbu_oi.lineidx' is Not Found
Updated
2 years ago
Comments count
2
Missing file 'train+val_img_frcnn_feats.pt'
Updated
2 years ago
Run inference on own picture with externally inputted object labels and bounding boxes
Updated
2 years ago
About od model to generate coco_caption features. I cannot reproduce your feature results.
Updated
2 years ago
Comments count
3
Image Captioning on COCO Val Set Mismatches with Images
Updated
2 years ago
Comments count
1
Question about tensor size difference in modeling_bert.py
Updated
2 years ago
Can i use this repo for training another dataset.
Updated
2 years ago
Question Related to VIVO Pre-training
Updated
2 years ago
Why all rows of attention map are the same (precision=3)?
Updated
2 years ago
How to get the checkpoint of OSCAR+?
Updated
2 years ago
Comments count
1
image caption task reproduce results weird
Updated
2 years ago
Comments count
1
Download links of dataset and model checkpoints are not working
Closed
2 years ago
Comments count
1
Loss values is nan when fine tuning on Oscar for captioning task
Updated
2 years ago
How to create train_caption.json on Flickr8k dataset? [Image Captioning task]
Closed
3 years ago
Comments count
4
Change the size of the region features
Updated
3 years ago
BrokenPipeError: [Errno 32] Broken pipe
Updated
3 years ago
Comments count
2
Cannot completely download the coco caption dataset for finetuning VinVL model
Updated
3 years ago
Comments count
3
Fine tune on the dataset with larger word dictionary?
Updated
3 years ago
Getting extremely low scores for nocaps evaluation
Updated
3 years ago
Comments count
4
Where do download vqa and gqa with VinVL features ?
Updated
3 years ago
Previous
Next