MCPcopy Create free account
hub / github.com/DeepRec-AI/DeepRec / QuantizeWeights

Function QuantizeWeights

tensorflow/lite/tools/optimize/quantize_weights.cc:546–555  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

544
545namespace internal {
546TfLiteStatus QuantizeWeights(flatbuffers::FlatBufferBuilder* builder,
547 const Model* input_model,
548 uint64_t weights_min_num_elements,
549 bool use_hybrid_evaluation) {
550 // By default we require that only weights with more than
551 // kWeightsMinSizeDefault elements are quantized.
552 CustomOpMap custom_op_map;
553 return QuantizeWeightsInt8(builder, input_model, use_hybrid_evaluation,
554 weights_min_num_elements, custom_op_map);
555}
556} // namespace internal
557
558TfLiteStatus QuantizeWeights(flatbuffers::FlatBufferBuilder* builder,

Callers 3

TEST_FFunction · 0.70
ExportFunction · 0.50

Calls 2

QuantizeWeightsInt8Function · 0.85
QuantizeWeightsFloat16Function · 0.85

Tested by 1

TEST_FFunction · 0.56