MCPcopy Create free account
hub / github.com/MotrixLab/MotionDiffuse / ModelVarType

Class ModelVarType

text2motion/models/gaussian_diffusion.py:286–297  ·  view source on GitHub ↗

What is used as the model's output variance. The LEARNED_RANGE option has been added to allow the model to predict values between FIXED_SMALL and FIXED_LARGE, making its job easier.

Source from the content-addressed store, hash-verified

284
285
286class ModelVarType(enum.Enum):
287 """
288 What is used as the model's output variance.
289
290 The LEARNED_RANGE option has been added to allow the model to predict
291 values between FIXED_SMALL and FIXED_LARGE, making its job easier.
292 """
293
294 LEARNED = enum.auto()
295 FIXED_SMALL = enum.auto()
296 FIXED_LARGE = enum.auto()
297 LEARNED_RANGE = enum.auto()
298
299
300class LossType(enum.Enum):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected