SEOKHUN CHO comments

Repositories
Issues
Comments

Results 2 comments of


                                            SEOKHUN CHO

Question about Conv-layer and Conv_Block

> @jihwan722 , please use a 3x3 conv layer with stride 3 to shrink the input size from 112x176 to 37x59 first. Code about classifier is not included in main_outside.py....

Method of temporal_transform and Backward

Additionally, in dataset.py, for the get_training_set, the n_samples_for_each_video for inside and outside differ, being 1 and 10 respectively, which results in different lengths for the dataloaders. Have these been unified...