Search Options

Results per page
Sort
Preferred Languages
Advance

Results 11 - 11 of 11 for uniform_dequantize (0.23 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/passes/quantized_function_library_uniform_quantized.mlir 

      // Dequantize final graph output back to f32. Input is qint8.
  func.func @dequantize_i8(%input : tensor<*x!tf_type.qint8>, %input_scale : tensor<*xf32>, %input_zp : tensor<*xi32>) -> tensor<*xf32> {
    %dequantize = "tf.UniformDequantize"(%input, %input_scale, %input_zp) {
      Tin = "tfdtype$DT_QINT8",
      Tout = "tfdtype$DT_FLOAT",
      quantization_axis = -1,
      quantization_min_val = -128,
      quantization_max_val = 127,
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Aug 29 01:13:58 UTC 2023
    - 19.3K bytes
    - Viewed (0)
Back to top