- Sort Score
- Result 10 results
- Languages All
Results 11 - 17 of 17 for dynamic_slice (0.2 sec)
-
tensorflow/compiler/jit/increase_dynamism_for_auto_jit_pass_test.cc
Const(zero_32)))); std::vector<string> compile_time_constant_inputs; compile_time_constant_inputs.push_back("size"); auto m_dynamic_slice = NodeWith( Op("Slice"), AssignedDevice(kDeviceName), Attr(kXlaCompileTimeConstantInputsAttr, compile_time_constant_inputs), Inputs(m_input, m_begin_s64, m_dynamic_slice_size));
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Feb 22 08:47:20 UTC 2024 - 18.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf.cc
// indices randomly generated via HLO rng_uniform ops. Otherwise, it is // translated into an HLO while op to first emulate shuffling indices using // HLO dynamic_slice and dynamic_update_slice ops, then finally HLO gather // with the shuffled indices. class ConvertRandomShuffleOp : public OpRewritePattern<TF::RandomShuffleOp> { public: using OpRewritePattern::OpRewritePattern;
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/tfrt/tests/tf_to_corert/fallback.mlir
%handle, %flow = "tf.TensorArrayV3"(%size) {clear_after_read = true, device = "/job:localhost/replica:0/task:0/device:CPU:0", dtype = f32, dynamic_size = false, element_shape = #tf_type.shape<?x512>, identical_element_shapes = true, tensor_array_name = "output"} : (tensor<i32>) -> (tensor<2x!tf_type.resource<tensor<1x512xf32>>>, tensor<f32>)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 00:18:59 UTC 2024 - 9.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfrt/tests/mlrt/while_to_map_fn.mlir
// CHECK: "tf.TensorArrayV3"
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 23 06:40:22 UTC 2024 - 68.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir/vhlo.mlir
//CHECK-NEXT:} func.func @dyanmic_slice(%arg0: tensor<3x3xi64>, %arg1: tensor<i64>, %arg2: tensor<i64>) -> tensor<3x3xi64> { %0 = "vhlo.dynamic_slice_v1"(%arg0, %arg1, %arg2) <{ slice_sizes = #vhlo.tensor_v1<dense<[3, 3]> : tensor<2xi64>> }> : (tensor<3x3xi64>, tensor<i64>, tensor<i64>) -> tensor<3x3xi64> return %0 : tensor<3x3xi64> }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 14 19:15:40 UTC 2024 - 31.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/legalize_hlo.cc
Type start_indices_element_type = mlir::cast<ShapedType>(op.getStartIndices().front().getType()) .getElementType(); // The mhlo dynamic_slice's start_indices can be either signed/unsigned // int32/int64. However, TF only takes in either i32 or i64 types for begin, // so we will always put a cast. Type signed_start_indices_element_type;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 154.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_generated_ops.td
} def TF_XlaDynamicSliceOp : TF_Op<"XlaDynamicSlice", [Pure, TF_NoConstantFold]> { let summary = "Wraps the XLA DynamicSlice operator, documented at"; let description = [{ https://www.tensorflow.org/performance/xla/operation_semantics#dynamicslice . DynamicSlice extracts a sub-array from the input array at dynamic start_indices. The size of the slice in each dimension is passed in
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 793K bytes - Viewed (0)