AggMan96 / RK-Net

Code for RK-Net

AggMan96/RK-Net Issues

some problem
Updated 2 months ago1
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [8, 1, 96, 96]], which is output 0 of ReluBackward0, is at version 4; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
Updated a year ago
In the same model, why should these four data sets be trained together?
Closed a year ago2
The computer's GPU memory is only 6G. Can I run this program?
Closed a year ago2
Training files for CVUSA and CVACT datasets
Updated 2 years ago
No such file or directory: './model/RK-Net'
Closed 2 years ago
Keypoint Visualization
Updated 2 years ago4
Queries regarding implementation
Updated 2 years ago