- Sort Score
- Result 10 results
- Languages All
Results 51 - 60 of 140 for Axis (0.04 sec)
-
tensorflow/compiler/mlir/lite/experimental/tac/transforms/device_transform_patterns.cc
new_shape, &rewriter); reshape_ops.push_back(reshape_op.getResult()); } // Deal with the axis. // We don't need to handle axis < 0, since it's counting reversely. int32_t axis = concat_op.getAxis(); if (axis >= 0) { axis += (4 - rank); } // Replace with the new concat op. SmallVector<int64_t, 4> new_output_shape; for (int i = 0; i < 4 - rank; ++i) {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 25.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/tests/pick-subgraphs.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 24.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/ir/tfl_ops.td
The new axis is created at dimension `axis` (default: the new axis is appended at the end). }]; let arguments = (ins TFL_TensorOf<[I32, I64]>:$indices, TFL_I32Tensor:$depth, TFL_TensorOf<[F32, I32, I64, I1, I8, UI8]>:$on_value, TFL_TensorOf<[F32, I32, I64, I1, I8, UI8]>:$off_value, I32Attr:$axis ); let results = (outs
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jun 06 19:09:08 UTC 2024 - 186K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/uniform_quantized_types.h
} // Returns true iff `type` is a uniform quantized type whose storage type is // 8-bit integer and expressed type is f32. bool IsI8F32UniformQuantizedType(Type type); // Returns true iff `type` is a uniform quantized per-axis (per-channel) type // whose storage type is 8-bit integer and expressed type is f32. bool IsI8F32UniformQuantizedPerAxisType(Type type); // Returns true iff `type` is a uniform quantized type whose storage type is
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 5.7K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_ops_n_z.cc
int64_t value_rank = value_type.getRank(); int64_t axis = op.getAxis(); if (axis < -value_rank || axis >= value_rank) return op.emitOpError("axis attribute must be in the range of [-") << value_rank << ", " << value_rank << ')'; axis = GetDimForAxis(axis, value_rank); int64_t dim_size = value_type.getDimSize(axis); if (ShapedType::isDynamic(dim_size)) return success();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 09 22:07:10 UTC 2024 - 170.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/ops/tf_op_quant_spec.cc
spec->biases_params[2] = {{0, 1}, quant::GetUniformQuantizedTypeForBias}; } } else if (function_name.contains("gather")) { // Note that gather has axis attribute that specifies channel axis. spec->coeff_op_quant_dim[0] = -1; } for (auto quantizable_operand : spec->coeff_op_quant_dim) { spec->quantizable_operands.insert(quantizable_operand.first); } }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 6.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/unroll_batch_matmul.cc
Type packed_type = RankedTensorType::get( {bcast.output_batch_size(), rows, cols}, element_type); const auto axis = rewriter.getI64IntegerAttr(0); auto pack_op = rewriter.create<TF::PackOp>(loc, packed_type, /*values=*/matmuls, axis); // Reshape the rank-3 tensor into the correct output shape. const auto& result_batch_shape = bcast.output_batch_shape().dim_sizes();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 11.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/legalize_hlo_conversions/dot_general.cc
{static_cast<int>( dot_dimensions_info.batch_dimensions().AxesArray().size())}, builder.getIntegerType(32)), operand_shape, batch_axes_tensor, /*axis*/ 0, /*batch_dims*/ 0); flattend_shape_values.push_back(batch_dims); } else { llvm::SmallVector<int32_t> batch_i32_vec; for (int64_t element :
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 19.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/canonicalize.mlir
// ----- // CHECK-LABEL: @RemoveRedundantUnpackPack func.func @RemoveRedundantUnpackPack(%arg0: tensor<2x5xf32>) -> tensor<2x5xf32> { %0:2 = "tfl.unpack"(%arg0) {axis = 0 : i32, num = 2 : i32} : (tensor<2x5xf32>) -> (tensor<5xf32>, tensor<5xf32>) %1 = "tfl.pack"(%0#0, %0#1) {axis = 0 : i32, values_count = 2 : i32} : (tensor<5xf32>, tensor<5xf32>) -> (tensor<2x5xf32>) func.return %1: tensor<2x5xf32> // CHECK-NOT: pack
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 20.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/canonicalize.mlir
func.return } // CHECK-LABEL: testGatherToV2 // Ensures that axis param and batch_dims attr use their default values of 0. func.func @testGatherToV2(%params: tensor<4x3xf32>, %indices: tensor<1x2xi32>) -> tensor<2x3xf32> { // CHECK: %[[AXIS:.*]] = "tf.Const"() <{value = dense<0> : tensor<i32>}> : () -> tensor<i32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 09 22:07:10 UTC 2024 - 132.1K bytes - Viewed (0)