MCPcopy Create free account
hub / github.com/FunAudioLLM/ThinkSound / forward

Method forward

ThinkSound/training/losses/auraloss.py:155–169  ·  view source on GitHub ↗

Calculate forward propagation. Args: input (Tensor): Predicted signal (B, #channels, #samples). target (Tensor): Groundtruth signal (B, #channels, #samples). Returns: Tensor: Filtered signal.

(self, input, target)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected