- Sort Score
- Result 10 results
- Languages All
Results 31 - 40 of 56 for h_scale (0.1 sec)
-
tensorflow/compiler/mlir/tfr/tests/rewrite_quantized_io.mlir
tfr.func @tf__my_requantize(%input: !tfr.tensor) -> !tfr.tensor { %raw_data = tfr.quant_raw_data(%input) : (!tfr.tensor) -> !tfr.tensor %scale, %zp = tfr.quant_qparam(%input) : (!tfr.tensor) -> (!tfr.tensor, !tfr.tensor) %result = tfr.call @tf__requantize(%raw_data, %scale, %zp) : (!tfr.tensor, !tfr.tensor, !tfr.tensor) -> !tfr.tensor tfr.return %result : !tfr.tensor } // CHECK-LABEL: @tf__intermediate
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 2.3K bytes - Viewed (0) -
src/cmd/vendor/github.com/google/pprof/internal/measurement/measurement.go
} } return false } // Scale a measurement from a unit to a different unit and returns // the scaled value and the target unit. The returned target unit // will be empty if uninteresting (could be skipped). func Scale(value int64, fromUnit, toUnit string) (float64, string) { // Avoid infinite recursion on overflow. if value < 0 && -value > 0 { v, u := Scale(-value, fromUnit, toUnit) return -v, u }
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Fri May 31 19:48:28 UTC 2024 - 8.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/device_target.h
OutputInputSameScale, OutputInputFreeScale, CustomScale, }; // Each kernel signature has its own specification for scales. struct KernelSpec { // Scale constraint ScaleConstraintType type; // Custom function to derive the scales. Only available when the scale // constraint is `CustomScale`. ScaleFn scale_fn; }; class KernelSpecs { public: using Signature = llvm::SmallVector<quant::AnyQuantizedType, 4>;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Mar 08 10:41:08 UTC 2024 - 7.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/prepare_lifting.td
// Converts tf.FusedBatchNormV3 into a sequence of more primitive arithmetic // operations. Specifically, performs the following calculation: // // (x - mean) * scale / sqrt(variance + epsilon) + offset // // Let multiplier = scale / sqrt(variance + epsilon), // to compute // (x - mean) * scale / sqrt(variance + epsilon) + offset, // is then to compute // (x * multiplier) + (offset - mean * multiplier). //
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 14 03:24:59 UTC 2024 - 8.4K bytes - Viewed (0) -
cmd/kube-controller-manager/app/autoscaling.go
// we don't use cached discovery because DiscoveryScaleKindResolver does its own caching, // so we want to re-fetch every time when we actually ask for it scaleKindResolver := scale.NewDiscoveryScaleKindResolver(hpaClient.Discovery()) scaleClient, err := scale.NewForConfig(hpaClientConfig, controllerContext.RESTMapper, dynamic.LegacyAPIPathResolverFunc, scaleKindResolver) if err != nil { return nil, false, err }
Registered: Sat Jun 15 01:39:40 UTC 2024 - Last Modified: Thu Mar 07 01:37:36 UTC 2024 - 4.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/end2end/quant_stats.pbtxt
# CHECK-NEXT: scale: [ 0.015686 ], # CHECK-NEXT: zero_point: [ 128 ] # CHECK-NEXT: }, # CHECK-NEXT: has_rank: true # CHECK-NEXT: }, { # CHECK-NEXT: shape: [ 4 ], # CHECK-NEXT: type: UINT8, # CHECK-NEXT: buffer: 2, # CHECK-NEXT: name: "input1", # CHECK-NEXT: quantization: { # CHECK-NEXT: scale: [ 0.023529 ],
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 4K bytes - Viewed (0) -
staging/src/k8s.io/apiextensions-apiserver/pkg/apis/testdata/HEAD/apiextensions.k8s.io.v1beta1.CustomResourceDefinition.json
"reason": "reasonValue", "fieldPath": "fieldPathValue", "optionalOldSelf": true } ] } }, "subresources": { "status": {}, "scale": { "specReplicasPath": "specReplicasPathValue", "statusReplicasPath": "statusReplicasPathValue", "labelSelectorPath": "labelSelectorPathValue" } }, "versions": [ {
Registered: Sat Jun 15 01:39:40 UTC 2024 - Last Modified: Wed Feb 28 19:06:46 UTC 2024 - 8.6K bytes - Viewed (0) -
staging/src/k8s.io/apiserver/pkg/util/openapi/enablement_test.go
Default:...
Registered: Sat Jun 15 01:39:40 UTC 2024 - Last Modified: Wed Apr 24 18:25:29 UTC 2024 - 4.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/passes.td
the third argument is the inverse scale constant (element type: float). * A tensor is dequantized using a `func::FuncOp` whose name contains "uniform_dequantize". The first argument is the tensor to be quantized, the second argument is the zero point constant (element type: int) and the third argument is the inverse scale constant (element type: float).
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 21:59:06 UTC 2024 - 5.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/ops/stablehlo_op_quant_spec.h
namespace mlir::quant::stablehlo { // Returns StableHLO quantization specs for an op. std::unique_ptr<OpQuantSpec> GetStableHloOpQuantSpec(Operation* op); // Returns quantization constraints (ex: fixed output, same scale) given // a StableHLO op. std::unique_ptr<OpQuantScaleSpec> GetStableHloQuantConstraints(Operation* op); // Checks if an op is quantizable in StableHLO quantizer. Argument op is not // necessarily a StableHLO op.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 03 05:11:03 UTC 2024 - 1.7K bytes - Viewed (0)