Hongbo Zhu

Problem with training on macOS

1

I came across a problem when I train GG-CNN on Cornell Dataset on my MacBook Pro (15-inch, 2019) python train_ggcnn.py --description training_example --network ggcnn --dataset cornell --dataset-path Cornell_Grasping_Dataset/ INFO:root:Loading Cornell...

def post_process_output(q_img, cos_img, sin_img, width_img): width_img = width_img.cpu().numpy().squeeze() *150.0 Hi Dougsm, What does * 150.0 use for, and why do we need to use it here? Thanks, Hongbo

The relprop method of the Linear layer

1

HI Chefer, Is there a typo with Lines 218 to 219 https://github.com/hila-chefer/Transformer-Explainability/blob/c3e578f76b954e8528afeaaee26de3f07e3fe559/modules/layers_ours.py#L218-L219 which should be the below? `S1 = safe_divide(R, Z1)` `S2 = safe_divide(R, Z2)` according to https://github.com/wjNam/Relative_Attributing_Propagation/blob/7fa96822740591b605712f251e556ec8487d1eea/modules/layers.py#L268-L269C36 Thanks, Hongbo

Could this package be used on Text classification tasks?

Can't download your BDD-OIA dataset from your google drive link

3

Hi all, Access was denied when I tried to download your dataset using the link below. https://drive.google.com/open?id=1NzF-UKaakHRNcyghtaWDmc-Vpem7lyQ6 Could you please check this issue? Thanks, Hongbo