Search Options

Results per page
Sort
Preferred Languages
Advance

Results 21 - 21 of 21 for numBits (0.11 sec)

  1. tensorflow/compiler/mlir/quantization/tensorflow/python/quantize_model.py

                _QuantizationComponent.COMPONENT_ACTIVATION
            ].tensor_type
        )
        # Unlike the HISTOGRAM_PERCENTILE method, the HISTOGRAM_MSE method uses
        # num_bits because it actually quantizes and dequantizes values.
        if activation_tensor_type != _TensorType.TENSORTYPE_INT_8:
          raise ValueError(
              'Only TENSORTYPE_INT_8 is supported for HISTOGRAM_MSE calibration'
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Fri May 17 03:36:50 UTC 2024
    - 34.2K bytes
    - Viewed (0)
Back to top