MCPcopy Create free account
hub / github.com/DeepGraphLearning/DiffPack / sample_train_t

Method sample_train_t

diffpack/schedule.py:281–290  ·  view source on GitHub ↗

Sample timesteps from uniform distribution. Args: shape (tuple): shape of the timesteps Returns: Tensor: timesteps of shape :math:`(shape)`

(self, shape)

Source from the content-addressed store, hash-verified

279 return x_prev
280
281 def sample_train_t(self, shape):
282 """Sample timesteps from uniform distribution.
283
284 Args:
285 shape (tuple): shape of the timesteps
286
287 Returns:
288 Tensor: timesteps of shape :math:`(shape)`
289 """
290 return torch.rand(shape)
291
292 @property
293 def reverse_t_schedule(self):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected