MCPcopy Create free account
hub / github.com/cwitkowitz/amt-tools / forward

Method forward

amt_tools/models/onsetsframes.py:505–575  ·  view source on GitHub ↗

Feed features through the music language model. Parameters ---------- in_feats : Tensor (B x T x E) Input features for a batch of tracks, B - batch size T - number of frames E - dimensionality of input embeddings (dim_in)

(self, in_feats)

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