- Sort Score
- Result 10 results
- Languages All
Results 31 - 34 of 34 for calibration_options (0.38 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/python/type_casters.h
tensorflow::quantization::QuantizationOptions> {}; template <> struct type_caster<::stablehlo::quantization::CalibrationOptions> : public internal::SerializedProtobufCaster< ::stablehlo::quantization::CalibrationOptions> {}; template <> struct type_caster<tensorflow::SignatureDef> : public internal::SerializedProtobufCaster<tensorflow::SignatureDef> {};
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Mar 11 19:29:56 UTC 2024 - 6.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/calibrator/integration_test/custom_aggregator_op_test.py
from tensorflow.python.framework import ops from tensorflow.python.ops import array_ops from tensorflow.python.platform import test _CalibrationMethod = ( stablehlo_quant_config_pb2.CalibrationOptions.CalibrationMethod ) class CustomAggregatorTest(test.TestCase): def setUp(self): super(CustomAggregatorTest, self).setUp() ops.disable_eager_execution() def testBypassAndMinMax(self):
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 01:09:50 UTC 2024 - 5.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/passes.h
// Inserts custom aggregation operators for the calibration procedure. std::unique_ptr<OperationPass<func::FuncOp>> CreateInsertCustomAggregationOpsPass( const ::stablehlo::quantization::CalibrationOptions& calib_opts); // Replaces composite functions with quantized composite functions. After this // pass runs, functions in the given graph will be replaced with their quantized
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 10 04:07:09 UTC 2024 - 12.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/py_function_lib.py
Args: calibration_statistics_serialized: Serialized `CalibrationStatistics`. This will be the source to calculate min and max values from. calibration_options_serialized: Serialized `CalibrationOptions`. Specifies how the min / max should be calculated. Returns: (min_value, max_value): Min and max calculated using calib_opts. `None` upon error. """
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 31 05:32:11 UTC 2024 - 27.4K bytes - Viewed (0)