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

Class ModelVarType

mogen/models/utils/gaussian_diffusion.py:293–304  ·  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

291
292
293class ModelVarType(enum.Enum):
294 """
295 What is used as the model's output variance.
296
297 The LEARNED_RANGE option has been added to allow the model to predict
298 values between FIXED_SMALL and FIXED_LARGE, making its job easier.
299 """
300
301 LEARNED = enum.auto()
302 FIXED_SMALL = enum.auto()
303 FIXED_LARGE = enum.auto()
304 LEARNED_RANGE = enum.auto()
305
306
307class LossType(enum.Enum):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected