We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
https://github.com/GuyTevet/motion-diffusion-model/blob/8139dda55d90a58aa5a257ebf159b2ecfb78c632/model/mdm.py#L151C8-L151C8
class MDM(nn.Module): ...... def forward(self, x, timesteps, y=None): """ x: [batch_size, njoints, nfeats, max_frames], denoted x_t in the paper timesteps: [batch_size] (int) """ bs, njoints, nfeats, nframes = x.shape emb = self.embed_timestep(timesteps) # [1, bs, d] force_mask = y.get('uncond', False) if 'text' in self.cond_mode: enc_text = self.encode_text(y['text']) emb += self.embed_text(self.mask_cond(enc_text, force_mask=force_mask))
The text was updated successfully, but these errors were encountered:
Yes, that's possible at inference (but not in training) and can accelerate performance. If you are interested, you can send us a pull request.
Sorry, something went wrong.
@GuyTevet I send a PR here: #152
Why is it not possible during training ?
No branches or pull requests
https://github.com/GuyTevet/motion-diffusion-model/blob/8139dda55d90a58aa5a257ebf159b2ecfb78c632/model/mdm.py#L151C8-L151C8
The text was updated successfully, but these errors were encountered: