HomeSort by relevance Sort by last modified time
    Searched refs:Float16To32 (Results 1 - 2 of 2) sorted by null

  /external/libtextclassifier/lang_id/common/lite_base/
float16.h 27 // one first needs to convert it to a normal float, using Float16To32.
54 static inline float Float16To32(float16 f) {
  /external/libtextclassifier/lang_id/common/
embedding-network.cc 123 // identical, except for float16 (instead of float) and the Float16To32
133 y_data[j] += Float16To32(*weight_ptr) * scale;
207 multiplier *= Float16To32(embedding_matrix.quant_scales[feature_id]);
219 multiplier *= Float16To32(embedding_matrix.quant_scales[feature_id]);

Completed in 215 milliseconds