Vid-ODE

Vid-ODE copied to clipboard

Inplace Operation Error

2

Hi, thank you for your excellent work. I have run the train code, but I encountered inplace operation error in an adversarial loss. How can I solve it? Thank you!...

dsshim0125

Hi, that's a solid work. After reading your work "Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts", I want to know how it performs on my own...

qiuzhen8484

Why ODE in Encoder is implemented this way ?

1

Thanks for sharing this and Congrats on a nice paper. Starting from the line referenced (full code block underneath it), seems that ODE in the Encoder is not calling DiffeqSolver...

abdelwahed

Hi, Thanks a lot for your awesome work and efforts to share the code. I am actually amazed by the fact that the model generates the entire sequence of frames,...

lucasdevries

From: > conv_odegru.py (line 113): ` first_point_mu, first_point_std = self.encoder_z0(input_tensor=e_truth, time_steps=truth_time_steps, mask=mask, tracker=self.tracker) ` > base_conv_gru.py (line 127): ` last_yi, latent_ys = self.run_ode_conv_gru( input_tensor=input_tensor, mask=mask, time_steps=time_steps, run_backwards=self.run_backwards, tracker=tracker) ` >...

williambittner1