Adeelyousaf comments

Results 6 comments of


                                            Adeelyousaf

Getting this error when i load my resnet based model

any luck?

.conda/envs/mm_tracking/lib/python3.7/site-packages/mmdet/datasets/samplers/group_sampler.py", line 90, in init assert hasattr(self.dataset, 'flag') AssertionError

This is the configuration file I am using dataset_type = 'ImagenetVIDDataset' data_root = '/home/c3-0/datasets/ILSVRC2017data/ILSVRC/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) train_pipeline = [ dict(type='LoadMultiImagesFromFile'), dict(type='SeqLoadAnnotations', with_bbox=True,...

.conda/envs/mm_tracking/lib/python3.7/site-packages/mmdet/datasets/samplers/group_sampler.py", line 90, in init assert hasattr(self.dataset, 'flag') AssertionError

here is the snipet of self.dataset ![image](https://user-images.githubusercontent.com/28863441/182524479-f91df297-48ef-49c1-ac6d-5d82f3b5041c.png)

Train without --masks flag

@noahcao Hi, would you were able to do box tracking? Kind Regards

UCF-101 train-test split

@owaisCS did you happen to find any answer ? my results are slightly different from those reported on UCF-101 in a zero-shot setting.

How to train your model?

same