MCPcopy Create free account
hub / github.com/Sin3DM/Sin3DM / ModelVarType

Class ModelVarType

src/diffusion/gaussian_diffusion.py:76–87  ·  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

74
75
76class ModelVarType(enum.Enum):
77 """
78 What is used as the model's output variance.
79
80 The LEARNED_RANGE option has been added to allow the model to predict
81 values between FIXED_SMALL and FIXED_LARGE, making its job easier.
82 """
83
84 LEARNED = enum.auto()
85 FIXED_SMALL = enum.auto()
86 FIXED_LARGE = enum.auto()
87 LEARNED_RANGE = enum.auto()
88
89
90class LossType(enum.Enum):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected