Method get_input

sat/diffusion_video.py:189–190 · view source on GitHub ↗

(self, batch)

Source from the content-addressed store, hash-verified

187	return loss, loss_dict
188
189	def get_input(self, batch):
190	return batch[self.input_key].to(self.dtype)
191
192	@torch.no_grad()
193	def decode_first_stage(self, z):

shared_stepMethod · 0.95

log_videoMethod · 0.95

toMethod · 0.80

no test coverage detected