Home
last modified time | relevance | path

Searched refs:bias_scale (Results 1 – 2 of 2) sorted by relevance

/packages/modules/NeuralNetworks/common/
DOperationsUtils.cpp261 const double bias_scale = biasShape.scale; in GetQuantizedConvolutionMultipler() local
264 NN_OPS_CHECK(std::abs(input_product_scale - bias_scale) <= in GetQuantizedConvolutionMultipler()
265 1e-6 * std::min(input_product_scale, bias_scale)); in GetQuantizedConvolutionMultipler()
/packages/modules/NeuralNetworks/tools/api/
Dtypes.spec1132 * with zeroPoint of 0 and bias_scale == input_scale * filter_scale.
4313 * of 0 and bias_scale == input_scale * filter_scale. For filter tensor
4316 * 0 and bias_scale of 0. The actual scale of each value 'i' is equal to
4317 * bias_scale[i] = input_scale * filter_scale[i].
4358 * of 0 and bias_scale == input_scale * filter_scale. For filter tensor
4361 * 0 and bias_scale of 0. The actual scale of each value 'i' is equal to
4362 * bias_scale[i] = input_scale * filter_scale[i].
5748 * with zeroPoint of 0 and bias_scale == input_scale * filter_scale.
5751 * and bias_scale of 0. The actual scale of each value 'i' is equal to
5752 * bias_scale[i] = input_scale * filter_scale[i].
[all …]