- Sort Score
- Result 10 results
- Languages All
Results 151 - 160 of 1,054 for ShapeN (0.1 sec)
-
tensorflow/compiler/mlir/tfrt/ir/mlrt/tf_mlrt_tpu_ops.td
$mlir_module is a serialized MLIR module with a `main` function that contains target computation. $metadata is a serialized TPUCompileMetadataProto describing the shapes and types of the inputs to the computation, as well as a mapping onto the TPU pod topology.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Oct 04 21:25:31 UTC 2023 - 3.1K bytes - Viewed (0) -
tensorflow/compiler/jit/variable_info_util.h
// are specified in `variable_indices` argument. We snapshot tensors that back // resource variables since concurrent updates may modify the shape, and it is // important that the shapes used for compilation match the true shapes of the // buffers. // // We snapshot the entire set of resource variables as one atomic operation. // This models Read->* dependencies between resource variable operations. See
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Feb 14 21:57:02 UTC 2023 - 4.3K bytes - Viewed (0) -
tensorflow/c/checkpoint_reader.h
public: CheckpointReader(const string& filename, TF_Status* status); bool HasTensor(const string& name) const; const string DebugString() const; // Returns a map from variable names to their shapes. Slices of a partitioned // tensor are combined into a single entry. const TensorSliceReader::VarToShapeMap& GetVariableToShapeMap() const; // Returns a map from variable names to their data types. Slices of a
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Oct 12 08:49:52 UTC 2023 - 3.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/einsum.cc
/*shape=*/shape_tensor); } // Creates ReshapeOp with runtime calcuation of required shape to support // dynamic shapes. The shape is calculated by Shape and UnsortedSegmentProd op. // `reshape_segids` and `num_reshape_segids` for UnsortedSegmentProd is // calculated in `reshapeForBatchMatmul`. TF::ReshapeOp createReshapeOpForDynamic(Value value, ArrayRef<int64_t> shape,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 33.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/utils/xla_sharding_util.cc
location, concat_dim_type, concat_dimension_attr); // Correctly set output shapes of concat op output if output shape is // statically known. Since the shape of TPUExecute op must be the same // across logical devices, we refer to the shape of 0th logical device // computation output. mlir::Type output_type; auto input_type = mlir::cast<mlir::TensorType>(inputs[0].getType());
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 22 21:28:13 UTC 2024 - 34K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf.cc
if (ShapedType::isDynamic(num_index_dims)) return failure(); auto updates = op.getUpdates(); // Broadcast scalar `updates` in into expected shape as following shape: // updates.shape == indices.shape[:-1] + tensor.shape[indices.shape[-1]:] if (updates_ty.getRank() == 0 && (std::is_same<OpTy, TF::TensorScatterUpdateOp>::value || std::is_same<OpTy, TF::TensorScatterAddOp>::value)) {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 20:00:43 UTC 2024 - 291.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/passes/nchw_convolution_to_nhwc.cc
/*batch_group_count=*/op.getBatchGroupCountAttr(), /*precision_config=*/op.getPrecisionConfigAttr()); // Transpose the output of the `ConvolutionOp` back to the original op's // output shape so that users' shapes match. // [b, 0, 1, f] => [b, f, 0, 1] auto output_transpose_op = rewriter.create<mlir::stablehlo::TransposeOp>( new_convolution_op.getLoc(), /*resultType0=*/output_tensor_type,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 8.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/tests/legalize-tf.mlir
// CHECK-NEXT: %[[SHAPE0:.*]] = shape.shape_of %arg0 : tensor<?xi1> -> tensor<1xindex> // CHECK-NEXT: %[[SHAPE1:.*]] = shape.shape_of %arg1 : tensor<?x?x8xi32> -> tensor<3xindex> // CHECK-NEXT: %[[SHAPE2:.*]] = shape.shape_of %arg2 : tensor<?x?x8xi32> -> tensor<3xindex> // CHECK-NEXT: %[[SHAPEEQ1:.*]] = shape.cstr_eq %[[SHAPE1]], %[[SHAPE2]] : tensor<3xindex>, tensor<3xindex>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon May 06 18:46:23 UTC 2024 - 335.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/transforms/shape_inference_pass.cc
namespace mlir { namespace TF { namespace { #define GEN_PASS_DEF_TENSORFLOWSHAPEINFERENCEPASS #include "tensorflow/compiler/mlir/tensorflow/transforms/tf_passes.h.inc" // This transformation pass propagate shapes on the TensorFlow graph. // It is a ModulePass in order to be able to change function types. class ShapeInference : public impl::TensorFlowShapeInferencePassBase<ShapeInference> { public: ShapeInference() = default;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 12:49:45 UTC 2024 - 3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/translate/import_model.cc
return mlir::UnrankedTensorType::get( mlir::TF::ResourceType::get(builder.getContext())); } } else if (auto shape = node.attrs().Find("_output_shapes")) { if (shape->has_list() && shape->list().shape_size() == 1) { return ConvertToMlirTensorType(shape->list().shape().at(0), dtype, &builder); } } }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 01 11:17:36 UTC 2024 - 183.2K bytes - Viewed (0)