gusang

Results 9 comments of gusang

> > Great work! Are the pretrained models availabel? > > A pytorch version: https://github.com/BIGBALLON/distribuuuu/blob/master/distribuuuu/models/botnet.py, > > The results (the model trained by [distribuuuu](https://github.com/BIGBALLON/distribuuuu)) : > > model epoch total...

> @rookiiiie leave an email and i will send it to you. my email is:[email protected]

no...i think the file "HO3D_train_data.json" miss necessary information:(

> Hi, I found that the pose parameters and the 21 hand joints in the JSON annotation file of the HO3D dataset are different from the original dataset. Can you...

> Hello, @lzfff12 . Thanks for your excellent work. > > I tried to retrain the model on the HO3Dv2 dataset using your default settings for three times. However, the...

option.txt: ``` ====== Options ====== HO3D_root: E:/localPy/HFL-Net-main/data/ho3d_v2 blocks: 1 channels: 256 dex_ycb_root: D:/Git/data1/zhifeng/dex-ycb epochs: 60 evaluate: False host_folder: host_folder/ho3d inp_res: 256 lambda_joints2d: 100.0 lambda_objects: 500.0 lr: 0.0001 lr_decay_gamma: 0.7 lr_decay_step:...

> Your model seems to not converge since the mano_joints3d_loss is still very high. Have you tried to train on another machine? I tried on multiple machines and 9.38 is...

hello!About the file ho3d.py in folder 'dataset': ``` with open(train_label_root + '/ho3d_train_data.json', 'r') as f: data_ho3d = json.load(f) ``` Do you use the file 'ho3d_train_data.json' provided by the author? Its...

> Hello, @lzfff12 . Thanks for your excellent work. > I am looking forward to your reply. And thanks in advance for your help! hello,after alter,i have tried twice (the...