- Sort Score
- Result 10 results
- Languages All
Results 1 - 7 of 7 for UniformQuantizedClipByValue (0.65 sec)
-
tensorflow/compiler/mlir/quantization/stablehlo/tests/bridge/convert-tf-quant-types.mlir
// CHECK-DAG: %[[INPUT_QINT:.*]] = "tf.Cast"(%arg0) <{Truncate = false}> : (tensor<1x2x2x1xi32>) -> tensor<1x2x2x1x!tf_type.qint32> // CHECK: "tf.UniformQuantizedClipByValue"(%[[INPUT_QINT]], %[[MIN_QINT]], %[[MIN_QINT]] %output = "tf.UniformQuantizedClipByValue"(%arg0, %q_min, %q_min, %scale, %zp) {quantization_axis = -1 : i64, quantization_max_val = 2147483647 : i64, quantization_min_val = -2147483648 : i64} :
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 25.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/tests/legalize-tf-quant.mlir
tensor<f32>, tensor<i32>) -> tensor<3x2x!tf_type.qint32> func.return %0 : tensor<3x2x!tf_type.qint32> } //===----------------------------------------------------------------------===// // tf.UniformQuantizedClipByValue legalization //===----------------------------------------------------------------------===// // ----- // CHECK-LABEL: func @uniform_quantized_clip_by_value
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 09 01:25:29 UTC 2024 - 37.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/passes/bridge/legalize_tf_quant_test.cc
quantization_axis = -1 : i64, quantization_min_val = -2147483648 : i64, quantization_max_val = 2147483647 : i64 } : (tensor<f32>, tensor<f32>, tensor<i32>) -> tensor<!tf_type.qint32> %1 = "tf.UniformQuantizedClipByValue"(%0, %qmin, %qmax, %scales, %zps) { quantization_axis = -1 : i64, quantization_min_val = -2147483648 : i64, quantization_max_val = 2147483647 : i64
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Feb 29 18:43:55 UTC 2024 - 7.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/quantized_function_library_uniform_quantized.mlir
%qclip_max = "tf.Cast"(%i32_max_filled) {Truncate = false} : (tensor<*xi32>) -> tensor<*x!tf_type.qint32> %relu = "tf.UniformQuantizedClipByValue"(%input, %qclip_min, %qclip_max, %input_scale, %input_zp) { T = "tfdtype$DT_QINT32", quantization_axis = -1, quantization_min_val = -2147483648, quantization_max_val = 2147483647,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Aug 29 01:13:58 UTC 2023 - 19.3K bytes - Viewed (0) -
tensorflow/compiler/jit/mark_for_compilation_pass.cc
"ToBool", "TridiagonalSolve", "TridiagonalMatMul", "TruncatedNormal", "UniformDequantize", "UniformQuantize", "UniformQuantizedAdd", "UniformQuantizedClipByValue", "UniformQuantizedConvolution", "UniformQuantizedDot", "UniformRequantize", "Unique", "UniqueV2", "UpperBound", "UnsortedSegmentMax",
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 21 12:19:41 UTC 2024 - 85.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/tf-ops.mlir
%scales: tensor<2xf32>, %zps: tensor<i32>) -> () { // expected-error @below {{'tf.UniformQuantizedClipByValue' op quantization_axis is -1, scales must have 0 rank.}} %0 = "tf.UniformQuantizedClipByValue"(%operand, %min, %max, %scales, %zps) { quantization_axis = -1 : i64, quantization_min_val = -2147483648 : i64, quantization_max_val = 2147483647 : i64
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 23 14:40:35 UTC 2023 - 236.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_generated_ops.td
); TF_DerivedOperandTypeAttr T = TF_DerivedOperandTypeAttr<0>; let hasVerifier = 1; } def TF_UniformQuantizedClipByValueOp : TF_Op<"UniformQuantizedClipByValue", [Pure]> { let summary = "Perform clip by value on the quantized Tensor `operand`."; let description = [{
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 793K bytes - Viewed (0)