Giters
microsoft
/
Oscar
Oscar and VinVL
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1034
Watchers:
25
Issues:
201
Forks:
247
microsoft/Oscar Issues
Results for text-to-image retrieval on COCO
Updated
3 years ago
Read error when downloading datasets
Updated
3 years ago
Comments count
1
Some wrong description in https://github.com/microsoft/Oscar/blob/master/MODEL_ZOO.md
Updated
3 years ago
Comments count
1
Image idx and image file name matching error
Updated
3 years ago
AssertionError
Closed
3 years ago
Comments count
2
Where can I find finetuned OSCAR model (not VinVL)
Closed
3 years ago
Comments count
1
Why is the Pre-trained Models of coco_caption empty in "VinVL_DOWNLOAD.md" file?
Updated
3 years ago
Comments count
5
How to Visualize attention
Updated
3 years ago
Comments count
1
VinVL Release for VQA task?
Updated
3 years ago
checkpoint of Image Text Retrieval
Updated
2 years ago
Comments count
3
TypeError: cannot serialize '_io.TextIOWrapper' object
Closed
2 years ago
Comments count
3
is there the pretrain checkpoint for Oscar+?I only find the checkpoint which has been finetuned on coco_ir
Updated
2 years ago
Comments count
1
Is it possible if we train the model with another language?
Updated
3 years ago
Comments count
2
A JSONDecoder ERROR when inference:‘TypeError: __init__() missing 2 required positional arguments: 'doc' and 'pos'’
Updated
3 years ago
Comments count
1
VinVL Image captioning raises AttributeError: 'NoneType' object has no attribute 'img_feature_dim'
Updated
2 years ago
Comments count
5
Run Oscar with Pytorch1.7 and Cuda10.1
Closed
2 years ago
Comments count
2
Pre-extracted image features: COCO 2014 Train/Val Image Features (~50G) is wrong
Updated
3 years ago
Comments count
1
got bad result when predicting
Updated
3 years ago
Comments count
1
How to run VQA with my own dataset?
Updated
3 years ago
Comments count
1
will this repo show in huggingface?
Updated
3 years ago
object tags
Updated
2 years ago
Comments count
2
Clarification of results
Updated
3 years ago
Comments count
3
Question about class names in label.tsv for the captioning task
Closed
3 years ago
Comments count
2
About Vinvl R50-C4 model
Updated
2 years ago
Comments count
1
how to orgnize yaml file?
Updated
3 years ago
Comments count
1
Unable to Reproduce the results for VinVL+VIVO on NoCaps
Updated
3 years ago
Comments count
6
Unable to Reproduce the Baseline results for NLVR2 task
Updated
3 years ago
For Oscar(NOT Vinvl) image-text retrieval, where to find "imageid2idx.json"?
Updated
2 years ago
Comments count
2
nocaps inference
Updated
3 years ago
datasets/coco_caption/test.yaml
Updated
3 years ago
Comments count
1
nocaps
Updated
3 years ago
How to use Pre-exacted Image Features?
Closed
3 years ago
Comments count
1
Cannot find eval caption index file when testing image/text retrieval ..
Closed
3 years ago
Comments count
3
why dose the pretrain corpus have 100w coco_qa pairs?
Updated
3 years ago
Comments count
2
About attribute and object lable for the pointed or designated bounding box
Updated
3 years ago
Did you use beam search in captioning CIDEr optimizaiton finetuning ?
Updated
3 years ago
Pre-extracted Image Features: what OD model is used?
Closed
3 years ago
Comments count
2
In Oscar+, how to generate the downstream tasks' data?
Updated
3 years ago
Question on script code
Updated
3 years ago
Comments count
1
Question on evaluating model on Flickr8k dataset
Updated
3 years ago
question about mask during inference
Updated
3 years ago
File "./oscar/datasets/oscar_tsv.py", line 114, in __init__ img_feat_offset_map = self.img_feat_offset_map[dataset_name][chunk_id] KeyError: '0'
Updated
3 years ago
Comments count
1
Miss the "coco_flickr30k_googlecc_gqa_sbu_oi_x152c4big2exp168.yaml"???
Closed
3 years ago
Comments count
1
FileNotFoundError: [Errno 2] No such file or directory: '/usr/local/cuda/bin/nvcc': '/usr/local/cuda/bin/nvcc'
Updated
3 years ago
Comments count
3
How long did you finetuned the Oscar+ on the VQA task?
Updated
3 years ago
How to map the VinVL Features of Conceptual Caption to the original dataset?
Closed
3 years ago
Comments count
1
How long did you pertained the OSCAR/OSCAR+
Updated
2 years ago
Comments count
9
How to generate the trainval_ans2label.pkl file?
Updated
2 years ago
Comments count
3
Incomplete File, imageid2idx.json and Image Features
Updated
3 years ago
Comments count
3
Why is there no inference file published for each task?
Updated
3 years ago
Previous
Next