hanoonar/object-centric-ovd issues and pull requests

#26 - Data leakage while training

Issue - State: open - Opened by Lukas-Ma1 6 months ago

#25 - Result mismatch on OV-COCO

Issue - State: open - Opened by Lukas-Ma1 7 months ago

#24 - open-vocabulary object detection with MViT

Issue - State: open - Opened by fushh 11 months ago - 1 comment

#23 - How to Fine-tune？

Issue - State: closed - Opened by sixone-Jiang about 1 year ago

#22 - In any case, I can`t detect "person" by your model

Issue - State: closed - Opened by sixone-Jiang over 1 year ago

#21 - Failed to run the training for `LVIS_OVD_Base_PIS` config

Issue - State: closed - Opened by dongwhfdyer over 1 year ago

#20 - Reproduce the cross-dataset evaluation

Issue - State: closed - Opened by tmp12316 over 1 year ago - 1 comment

#19 - Questions about pseudo label in training with detection data.

Issue - State: closed - Opened by Edwardmark over 1 year ago - 4 comments
Labels: question

#18 - segmentation fault when training COCO_OVD_base_PIS.yaml

Issue - State: closed - Opened by haixpham almost 2 years ago

#17 - Open images weights

Issue - State: closed - Opened by ma-siddiqui almost 2 years ago - 1 comment

#16 - Results for 4x schedule on LVIS?

Issue - State: closed - Opened by Kyfafyd almost 2 years ago - 1 comment

#15 - Issues about ImageNet-21K

Issue - State: closed - Opened by gugite almost 2 years ago - 2 comments

#14 - Is there some difference in the baseline between Yours and PromptDet

Issue - State: closed - Opened by xushilin1 almost 2 years ago - 1 comment

#13 - Questions about the results

Issue - State: closed - Opened by th0214 about 2 years ago - 2 comments

#12 - query about the clip classification acc using gt boxes in Object-centric

Issue - State: closed - Opened by motoight about 2 years ago - 7 comments
Labels: question

#11 - Change Batch-size per GPU

Issue - State: closed - Opened by th0214 about 2 years ago - 1 comment
Labels: question

#10 - A question about the results of Open-vocabulary COCO

Issue - State: closed - Opened by SCUTjinchengli about 2 years ago - 4 comments
Labels: documentation

#9 - Adds interactive colab demo

Pull Request - State: closed - Opened by hanoonaR about 2 years ago

#8 - Using your pretrained models for ZSD on custom objects and images

Issue - State: closed - Opened by Ozziko about 2 years ago - 1 comment
Labels: documentation, enhancement

#7 - JSONDecodeError

Issue - State: closed - Opened by Millielele about 2 years ago - 4 comments

#6 - Question about MViT pre-training.

Issue - State: closed - Opened by YifanXu74 over 2 years ago

#5 - Error during class-specific IN-21K proposal generation for LVIS

Issue - State: closed - Opened by muzairkhattak over 2 years ago

#4 - Missing coco_props.tar.gz

Issue - State: closed - Opened by hq-deng over 2 years ago - 2 comments

#3 - Missing lvis_v1_train_norare_cat_info.json

Issue - State: closed - Opened by ma-siddiqui over 2 years ago - 2 comments
Labels: good first issue

#2 - Updates the external module (MAVL)

Pull Request - State: closed - Opened by mmaaz60 over 2 years ago

#1 - Update README.md