A S M Iftekhar

Command for training on BDD100K

7

Hello, Thanks a lot for your awesome work and congratulations for getting accepted at ECCV. I am planning to retrain the model on bdd100k dataset, in this [script](https://github.com/megvii-research/MOTR/blob/motr_bdd100k/configs/r50_motr_train.sh) from motr_bdd100k...

Query about "Other Relationships"

1

Hello, Thanks a lot your nice work. In the paper, you mentioned to evaluate on 25 classes, however, in your dataloader you have "Other Relationships" as a contact class which...

HACS Dataset: Action Recognition Model

1

Hello, Thanks for your excellent repository. I see from 'data/hacs_annotations/hacs_val_cls_top2.json', you predicted top-2 actions on the validation set of HACS. Do you have the same json files for the testing...

Confusion about Co-Occurance Matrics

2

Thanks for your beautiful work. I downloaded the pickle file 'co-occurrence_pos.pkl' and read it like this: ` with open('co-occurrence_pos(1).pkl', 'rb') as f: data = pickle.load(f) ` The output of data...

Thanks a lot for your beautiful work. While looking into the repository I got confused with something. In [data/dataset.py](https://github.com/Tushar-N/attributes-as-operators/blob/master/data/dataset.py) for commutative reguralizer: > def sample_affordance(self, attr, obj): > new_attr =...