MCPcopy Create free account
hub / github.com/TianzhongSong/Tensorflow-quantization-test / SSDInputEncoder

Class SSDInputEncoder

utils/ssd_input_encoder.py:21–598  ·  view source on GitHub ↗

Transforms ground truth labels for object detection in images (2D bounding box coordinates and class labels) to the format required for training an SSD model. In the process of encoding the ground truth labels, a template of anchor boxes is being built, which are subsequent

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