Giters
ashkamath
/
mdetr
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
952
Watchers:
19
Issues:
96
Forks:
126
ashkamath/mdetr Issues
Long caption issue
Updated
2 months ago
Comments count
1
requirements for running the demo notebook
Updated
2 months ago
Comments count
1
Generate tokens_positive for just COCO for pre-training!!
Closed
4 months ago
Minor Typo in eval_lvis.py
Updated
4 months ago
Bbox assertion error when using ENB models (eval & pretrain as well): assert (boxes1[:, 2:] >= boxes1[:, :2]).all()
Updated
5 months ago
Comments count
7
Issues with training on a single node
Updated
7 months ago
How to decode GQA evaluation results
Closed
a year ago
Comments count
1
Can you provide the final_vg json files?
Updated
8 months ago
CLEVR-REF+ training
Updated
8 months ago
run
Updated
10 months ago
finetune have bug!!ValueError: char_to_token() is not available when using Python based tokenizers
Updated
a year ago
Comments count
3
I would like to know how to use the model in clevr-ref+.
Closed
a year ago
ValueError: char_to_token() is not available when using Python based tokenizers
Updated
a year ago
Comments count
1
Weird results while evaluating & reproducing ENB3 model on PhraseCut
Closed
a year ago
issue #44 "I guess its uncompleted project so I gave up this essay"
Closed
a year ago
Comments count
1
how to view training on tensorboard
Closed
a year ago
Comments count
1
how to define positive tokens?
Closed
a year ago
Comments count
1
How to generate "tokens_negative" and "tokens_positive" when we convert our own dataset into mdetr annotations?
Closed
a year ago
Comments count
1
How to define "Negative Tokens" ?
Closed
a year ago
Comments count
1
With the increase of MDETR training time, GPU memory occupation keeps increasing. After several epoch training, memory explodes,i.e. OOM, out of memory.
Closed
a year ago
Comments count
1
[Colab Error] InvalidVersion: Invalid version: '0.10.1,<0.11'
Closed
a year ago
Comments count
2
Cannot find finetune_phrasecut_miniv.json
Closed
a year ago
Comments count
1
Pre-trained model gives nan prediction in Colab
Closed
2 years ago
Comments count
7
LVIS few shot finetuning configs
Closed
2 years ago
Missing pretrained checkpoint for ResNet101
Closed
2 years ago
Comments count
3
Test the model with single instance, and visualize the result
Closed
2 years ago
Comments count
2
colab sandbox is deactivated
Closed
2 years ago
Comments count
1
Seems cannot verify the existence of objects
Closed
2 years ago
Comments count
2
Pre-training question
Updated
2 years ago
annotations for clevr
Closed
3 years ago
Comments count
1
cat2obj.json
Updated
2 years ago
How are you normalizing the GT bounding boxes ?
Closed
2 years ago
Preprocessing scripts for CLEVR dataset.
Updated
2 years ago
How to generate `tokens_positive` for the sentence using Spacy in the Referring Expression Comprehension task?
Closed
2 years ago
Comments count
1
Query regarding Flickr MergeBox protocol evaluations
Updated
2 years ago
Question about bounding box format
Closed
2 years ago
Comments count
2
Doubts regarding pretraining
Closed
2 years ago
Comments count
3
Logs for the fine tuning on LVIS detection
Updated
2 years ago
Comments count
6
Cannot find phrasecut annotation files
Closed
2 years ago
Comments count
2
extra LN at the end of encoder is removed
Closed
2 years ago
Comments count
3
Cuda error: out of memory when finetuning on the refcoco dataset
Closed
2 years ago
Comments count
1
No such file or directory: 'mdetr_annotations/finetune_phrasecut_train.json'
Closed
2 years ago
Comments count
1
preprocessd annotations
Closed
2 years ago
Comments count
1
How to test on CLEVR?
Closed
2 years ago
Why is `model_ema` not saved in `BEST_checkpoint.pth`?
Updated
2 years ago
finetuning on refcoco
Closed
2 years ago
Question about GQA test-dev evaluation.
Closed
2 years ago
Comments count
2
Questions on contrastive alignment loss
Closed
2 years ago
How to train DETR on provided LVIS 1%/10%/100% dtaset
Updated
3 years ago
How to make the custom dataset and train it?
Updated
3 years ago
Previous
Next