- Sort Score
- Result 10 results
- Languages All
Results 91 - 100 of 1,404 for tensor2 (0.14 sec)
-
tensorflow/compiler/mlir/lite/tests/mlir2exec/tfl_while_op.mlir
%1 = "tfl.sub"(%arg2, %arg4) {fused_activation_function = "NONE"} : (tensor<*xi32>, tensor<i32>) -> tensor<*xi32> %2 = tfl.add %arg3, %arg3 {fused_activation_function = "NONE"} : tensor<*xf32> "tfl.yield"(%1, %2, %arg4) : (tensor<*xi32>, tensor<*xf32>, tensor<i32>) -> () }) : (tensor<i32>, tensor<1xf32>, tensor<i32>) -> (tensor<i32>, tensor<1xf32>, tensor<i32>) func.return %0#1, %0#2 : tensor<1xf32>, tensor<i32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 19 17:11:31 UTC 2022 - 2.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer/svdf_v2.mlir
// CHECK-EMPTY: ^bb0(%arg0: tensor<4 x f32>, %arg1: tensor<4 x i8>, %arg2: tensor<4 x f32>, %arg3: tensor<4 x f32>): %0 = "tfl.pseudo_const" () {value = dense<0.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const") %1 = "tfl.svdf"(%arg0, %arg1, %arg2, %arg3, %0) {fused_activation_function = "RELU", rank = 2 : i32} : (tensor<4xf32>, tensor<4xi8>, tensor<4xf32>, tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> func.return %1 : tensor<4xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jul 14 16:41:28 UTC 2022 - 3.7K bytes - Viewed (0) -
tensorflow/cc/framework/gradient_checker.cc
std::vector<Tensor>* x_datas, std::vector<Tensor>* jacobian_ts) { size_t y_num = y_shapes.size(); size_t x_num = x_shapes.size(); // x_stride and y_stride are used to calculate the correct jacobian row and // column position for a pair of elements at positions r, c within the x and y // tensors respectively.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sat Apr 13 05:57:22 UTC 2024 - 18.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer/logical.mlir
%0 = "tfl.pseudo_const" () {value = dense<true> : tensor<4xi1>} : () -> tensor<4xi1> loc("Const1") %1 = "tfl.pseudo_const" () {value = dense<false> : tensor<4xi1>} : () -> tensor<4xi1> loc("Const2") %2 = "tfl.logical_or"(%arg0, %1) : (tensor<4xi1>, tensor<4xi1>) -> tensor<4xi1> loc("logical_or") %3 = "tfl.logical_and"(%2, %0) : (tensor<4xi1>, tensor<4xi1>) -> tensor<4xi1> loc("logical_and") func.return %3 : tensor<4xi1>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jul 14 16:41:28 UTC 2022 - 3.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow_to_stablehlo/README.md
type `tensor<?x3x224x224xf32>`. ```bash tf-to-stablehlo-translate <saved-model-path> --input-arg-shapes=4,3,224,224 ``` * To convert [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-uncased) to StableHLO with static input shapes `1x12`, `1x12`, and `1x12` for input arguments with types `tensor<?x?xi32>, tensor<?x?xi32>, tensor<?x?xi32>`. ```bash
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 21 22:58:42 UTC 2024 - 4.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer/mul_v2.mlir
// CHECK-NEXT:} %0 = "tfl.pseudo_qconst"() { qtype = tensor<3x!quant.uniform<i8:f32, 0.1>>, value = dense<2> : tensor<3xi8>} : () -> tensor<3x!quant.uniform<i8:f32, 0.1>> %1 = "tfl.mul"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<3x!quant.uniform<i8:f32, 0.1>>, tensor<3x!quant.uniform<i8:f32, 0.1>>) -> tensor<3x!quant.uniform<i8:f32, 0.1>> loc("mul") func.return %1 : tensor<3x!quant.uniform<i8:f32, 0.1>>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jul 14 16:41:28 UTC 2022 - 2.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer/mul_v3.mlir
// CHECK-NEXT:} %0 = "tfl.pseudo_qconst"() { qtype = tensor<3x!quant.uniform<i8:f32, 1.0>>, value = dense<2> : tensor<3xi8>} : () -> tensor<3x!quant.uniform<i8:f32, 1.0>> %1 = "tfl.mul"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<3x!quant.uniform<i8:f32, 1.0>>, tensor<3x!quant.uniform<i8:f32, 1.0>>) -> tensor<3x!quant.uniform<i8:f32, 1.0>> loc("mul") func.return %1 : tensor<3x!quant.uniform<i8:f32, 1.0>>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jul 14 16:41:28 UTC 2022 - 2.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer/signature_def_with_no_inputs.mlir
func.func @main() -> (tensor<5xf32> {tf_saved_model.index_path = ["start_logits"]}) attributes {tf.entry_function = {control_outputs = "", inputs = "", outputs = "StatefulPartitionedCall:1"}, tf_saved_model.exported_names = ["serving_default"]} { %cst = arith.constant dense<0.000000e+00> : tensor<5xf32> func.return %cst : tensor<5xf32> }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jul 14 16:41:28 UTC 2022 - 1.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/save_model.py
) -> _SignatureDefMap: """Validates if the tensor names in signatures are consistent with the graph. This function checks if the input and output tensor names in the signatures exist if the graph. The output tensor names might change during conversion, we try to fix that with `_restore_output_tensor_names`. Besides, if there are duplicated tensor names, they we will be prefixed with the signature name.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 01:09:50 UTC 2024 - 12.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/mlir2flatbuffer/transpose_conv_optional.mlir
%0 = "tfl.transpose_conv"(%arg0, %arg1, %arg2, %cst) {padding = "SAME", stride_h = 2 : i32, stride_w = 2 : i32, fused_activation_function = "NONE"} : (tensor<4xi32>, tensor<32x4x4x128xf32>, tensor<1x32x42x128xf32>, none) -> tensor<1x64x84x32xf32> func.return %0 : tensor<1x64x84x32xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Dec 14 04:58:17 UTC 2022 - 2.8K bytes - Viewed (0)