ggcnn

ggcnn copied to clipboard

How to set parameters when train on Jacquard dataset

2

Hello , I want to train on jacquard datasets，I want wo know how to set parameters such as _batches-per-epoch_? Thanks~

JerryZhang24

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

Hongbo-Z

can the ggcnn deal with the image of different size

2

Can this network handle 1280*720 pictures

CodeKingWang

How to visualise with 3D graspping pose?

1

Hi Doug, thanks for your amazing work, I managed to run your project and get some results (Figure1) from cornell dataset and Jacquard dataset. My question is how to get...

yananliusdu


t-272

grasp.py问题

1

File "C:\Users\adminster\Desktop\yolo-ggcnn-main\yolo-ggcnn-main\ggcnn\train_ggcnn.py", line 253, in run test_results = validate(net, device, val_data, args.val_batches) File "C:\Users\adminster\Desktop\yolo-ggcnn-main\yolo-ggcnn-main\ggcnn\train_ggcnn.py", line 103, in validate val_data.dataset.get_gtbb(didx, rot, zoom_factor), File "C:\Users\adminster\Desktop\yolo-ggcnn-main\yolo-ggcnn-main\ggcnn\utils\data\jacquard_data.py", line 42, in get_gtbb gtbbs.rotate(rot, (c, c))...

zsgwq