Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for enable_two_input_tensors (0.43 sec)

  1. tensorflow/compiler/mlir/quantization/tensorflow/passes/lift_quantizable_spots_as_functions.cc

                  " except matmul and einsum.");
            } else if (!quant_options_.enable_two_input_tensors() &&
                       !is_unitwise_quantization_enabled) {
              return absl::InternalError(
                  "Quantization is disabled for this op due to the non-constant "
                  "weight. You can enable it by setting `enable_two_input_tensors` "
                  "to true or using unit-wise quantization config.");
            }
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Fri May 10 04:07:09 UTC 2024
    - 16.4K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/quantization/tensorflow/quantization_options.proto

      // Enables two inputs of an operation to be both tensors.
      // Currently supports MatMul and BatchMatMul ops for XLA.
      // TODO(b/263528090): Check the condition when this feature is beneficial.
      bool enable_two_input_tensors = 11;
    
      // Supports TPU model quantization. If the target model for the quantization
      // is already converted for TPU, this flag may be helpful. Note that this
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Mar 19 06:31:19 UTC 2024
    - 9.2K bytes
    - Viewed (0)
  3. tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test.py

                preset_method=_PresetMethod.METHOD_STATIC_RANGE_INT8
            ),
            tags=tags,
            signature_keys=[signature_key],
            op_set=quant_opts_pb2.XLA,
            enable_two_input_tensors=not use_kernel,
        )
    
        converted_model = quantize_model.quantize(
            self._input_saved_model_path,
            self._output_saved_model_path_2,
            quantization_options,
        )
    
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Fri May 17 03:36:50 UTC 2024
    - 235.6K bytes
    - Viewed (0)
Back to top