- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 5,375 for FusedN (0.12 sec)
-
test/used.go
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Mon Dec 28 08:39:17 UTC 2020 - 6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfr/README.md
this kernel in the inference graph. * *Solution*: The user should define a new TF op, which corresponds to the fused kernel, with composition, and use this op to build the model for both training and inference. For the platforms where a fused kernel is not available, the execution will use the composition instead. ## Gradient (TODO) ## Authoring Op Composition in Python
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 29 18:32:13 UTC 2022 - 6.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/quantization_info.proto
// tensor_name := op_name | op_name ’:’ port_number. // If the op has only one port, op_name can be used. // If the op has internal states, such as fused LSTM, the port_number should // follow a predefined convention. oneof name_oneof { string name = 1; // An regex can be used to match multiple tensors. string name_regex = 2; }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Oct 08 03:45:04 UTC 2019 - 2.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/utils/lstm_utils.h
constexpr char kCoupleInputForgetGates[] = "CoupleInputForgetGates"; // A utility class that enables the conversion of the LSTMCellSimple composite // op into a fused TFL LSTM op. The fused op is contained within a FuncOp // that also contains other supporting ops needed to construct the operands for // the fused op. The caller provides the containing FuncOp as input with // arguments specifying the input, weight, projection and bias.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sat Jun 03 00:14:05 UTC 2023 - 7.3K bytes - Viewed (0) -
.github/ISSUE_TEMPLATE/tflite-converter-issue.md
- Model produces wrong results and/or has lesser accuracy. - Model produces correct results, but it is slower than expected. ### 4. (optional) RNN conversion support If converting TF RNN to TFLite fused RNN ops, please prefix [RNN] in the title. ### 5. (optional) Any other info / logs
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 15 03:35:58 UTC 2022 - 2.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/api/v1/testdata/prepare_to_library.mlir
<{host_mlir_module = "#loc1 = loc(\22Reshape:\22)\0A#loc2 = loc(\22Reshape_4\22)\0A#loc3 = loc(\22Reshape\22)\0A#loc9 = loc(fused[#loc1, #loc2, #loc3])\0Amodule {\0A func.func @host_func(%arg0: tensor<3360x?xi32> loc(fused[#loc1, #loc2, #loc3]), %arg1: tensor<3xi32> loc(fused[#loc1, #loc2, #loc3]), %arg2: tensor<i32> loc(fused[#loc1, #loc2, #loc3]), %arg3: tensor<2xi32> loc(fused[#loc1, #loc2, #loc3])) -> (tensor<1x1120x?xi32>, tensor<1x1120x?xi32>, tensor<1120x?xi32>, tensor<2xi32>) {\0A %0 = \...
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jan 31 23:44:50 UTC 2024 - 2.3K bytes - Viewed (0) -
test/codegen/floats.go
return b0[idx] * b1 } func indexStore(b0 []float64, b1 float64, idx int) { // arm64:`FMOVD\sF[0-9]+,\s\(R[0-9]+\)\(R[0-9]+<<3\)` b0[idx] = b1 } // ----------- // // Fused // // ----------- // func FusedAdd32(x, y, z float32) float32 { // s390x:"FMADDS\t" // ppc64x:"FMADDS\t" // arm64:"FMADDS" // riscv64:"FMADDS\t" return x*y + z }
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Thu Apr 04 15:24:29 UTC 2024 - 4.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/lift_quantizable_spots_as_functions_xla_selective_quantization.mlir
} : (tensor<1x10xf32>, tensor<10x10xf32>) -> tensor<1x10xf32> loc(fused["MatMul:", "test_opt_out"]) %2 = "tf.Reshape"(%1, %cst_0) : (tensor<1x10xf32>, tensor<2xi32>) -> tensor<?x10xf32> loc(fused["Reshape:", "model/reshape"]) %3 = "tf.AddV2"(%2, %cst) : (tensor<?x10xf32>, tensor<10xf32>) -> tensor<?x10xf32> loc(fused["AddV2:", "model/add"]) func.return %3 : tensor<?x10xf32> } }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 6.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/graphdef2mlir/node-locations.pbtxt
} # TODO(b/142400497): What is the semantic contract for locations? # CHECK: "tf.Const"{{.*}}value = dense<2>{{.*}}loc(fused["Const:", "n1@f1", "n2@f2", "fused_node_outside_function"]) # CHECK: "tf.Const"{{.*}}value = dense<0>{{.*}}loc(fused["Const:", "node_outside_function"])
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Nov 15 19:42:47 UTC 2021 - 1.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/tests/import_quant_stats.mlir
func.func @import_stats_skip(%arg0: tensor<4xf32>, %cst: tensor<i32>) -> (tensor<2xf32>,tensor<2xf32>) { %0:2 = "tfl.split"(%cst, %arg0) {num_splits = 2 : i32} : (tensor<i32>, tensor<4xf32>) -> (tensor<2xf32>, tensor<2xf32>) loc(fused["skip1", "skip2.cc":10:8, callsite("op" at "skip3.cc":10:8)]) func.return %0#0, %0#1 : tensor<2xf32>, tensor<2xf32> // CHECK-NEXT: "tfl.split" // CHECK-NEXT: return } // CHECK-LABEL: import_stats_name
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 01 06:25:50 UTC 2024 - 2.8K bytes - Viewed (0)