- Sort Score
- Result 10 results
- Languages All
Results 1 - 5 of 5 for FakeQuantWithMinMaxVarsPerChannel (0.39 sec)
-
tensorflow/compiler/mlir/lite/tests/raise-custom-ops.mlir
%outputs_18, %control_19 = tf_executor.island wraps "tf.FakeQuantWithMinMaxVarsPerChannel"(%arg0, %outputs_16, %outputs_14) {device = "", narrow_range = true, num_bits = 8 : i64} : (tensor<*xf32>, tensor<186xf32>, tensor<186xf32>) -> tensor<*xf32> tf_executor.fetch %outputs_18 : tensor<*xf32> } func.return %0 : tensor<*xf32> // CHECK: tf_executor.island wraps "tf.FakeQuantWithMinMaxVarsPerChannel" // WRAPPED-NEXT: tf_executor.graph {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 4K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/tensorflow/tests/tf_to_quant.mlir
%arg2 = arith.constant dense<[255.0, 254.0, 256.0]> : tensor<3xf32> %0 = "tf.FakeQuantWithMinMaxVarsPerChannel"(%arg0, %arg1, %arg2) {num_bits = 5, narrow_range = false} : (tensor<8x3xf32>, tensor<3xf32>, tensor<3xf32>) -> tensor<8x3xf32> func.return %0 : tensor<8x3xf32> // CHECK: %[[fq:.*]] = "tf.FakeQuantWithMinMaxVarsPerChannel"(%arg0, %cst, %cst_0)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 9.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/tensorflow/tests/tf_to_quant_4bit.mlir
%arg2 = arith.constant dense<[15.0, 14.0, 16.0]> : tensor<3xf32> %0 = "tf.FakeQuantWithMinMaxVarsPerChannel"(%arg0, %arg1, %arg2) {num_bits = 3, narrow_range = false} : (tensor<8x3xf32>, tensor<3xf32>, tensor<3xf32>) -> tensor<8x3xf32> func.return %0 : tensor<8x3xf32> // CHECK: %[[fq:.*]] = "tf.FakeQuantWithMinMaxVarsPerChannel"(%arg0, %cst, %cst_0)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 9.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/convert_fake_quant_to_qdq.mlir
%0 = "tf.FakeQuantWithMinMaxVars"(%arg0, %cst, %cst_0) { device = "", narrow_range = false, num_bits = 8 : i64 } : (tensor<3xf32>, tensor<f32>, tensor<f32>) -> tensor<3xf32> %1 = "tf.FakeQuantWithMinMaxVarsPerChannel"(%arg1, %cst_1, %cst_2) { device = "", narrow_range = true, num_bits = 8 : i64 } : (tensor<4x3xf32>, tensor<3xf32>, tensor<3xf32>) -> tensor<4x3xf32> func.return %0, %1 : tensor<3xf32>, tensor<4x3xf32> }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 24 07:02:54 UTC 2022 - 2.3K bytes - Viewed (0) -
tensorflow/cc/framework/fuzzing/op_fuzzing.bzl
"ExtractImagePatches", "ExtractVolumePatches", "FakeQuantWithMinMaxArgs", "FakeQuantWithMinMaxArgsGradient", "FakeQuantWithMinMaxVars", "FakeQuantWithMinMaxVarsGradient", "FakeQuantWithMinMaxVarsPerChannel", "FakeQuantWithMinMaxVarsPerChannelGradient", "Fill", "Fingerprint", "Gather", "GuaranteeConst", "Identity", "IdentityN", "InplaceAdd", "InplaceSub",
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Nov 07 19:14:57 UTC 2022 - 4.3K bytes - Viewed (0)