MCPcopy Create free account
hub / github.com/BertaBescos/DynaSLAM / DetectionTargetLayer

Class DetectionTargetLayer

src/python/model.py:567–622  ·  view source on GitHub ↗

Subsamples proposals and generates target box refinment, class_ids, and masks for each. Inputs: proposals: [batch, N, (y1, x1, y2, x2)] in normalized coordinates. Might be zero padded if there are not enough proposals. gt_class_ids: [batch, MAX_GT_INSTANCES] Integer c

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

buildMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected