- Sort Score
- Result 10 results
- Languages All
Results 211 - 220 of 1,398 for TensorT (0.15 sec)
-
tensorflow/cc/saved_model/experimental/public/signature_def_function.h
// types (like optionals, generators, etc). Additionally, this flattening means // they will not preserve the exact interface of the original tf.function they // were traced from, as things like composite tensors decay into their // internal dense tensor representation. // Second, all inputs and outputs are "named", and these names are load bearing // (eg: they are part of the interface of tensorflow_serving):
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Aug 17 23:03:48 UTC 2020 - 4.5K bytes - Viewed (0) -
tensorflow/c/experimental/gradients/array_grad_test.cc
std::vector<AbstractTensorHandle*> temp_outputs(2); TF_RETURN_IF_ERROR( ops::IdentityN(ctx, inputs, absl::MakeSpan(temp_outputs), "IdentityN")); // Although, `ops::IdentityN` returns 2 tensors, the first tensor isn't needed // for computing gradient so we could safely drop it. outputs[0] = temp_outputs[1]; temp_outputs[0]->Unref(); return absl::OkStatus(); } class CppGradients
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 28 13:53:47 UTC 2024 - 5K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/ir/tfl_op_interfaces.td
let description = [{ The TensorFlow Lite dialect. This dialect maps to TensorFlow Lite operations. Invariants: * All values are of Tensor type (in particular, scalars are represented using zero-dimensional tensors); }]; let cppNamespace = "::mlir::TFL"; let useDefaultAttributePrinterParser = 1; let useDefaultTypePrinterParser = 1; let extraClassDeclaration = [{
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 4.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/common/tfl_pass_config.h
// Whether to convert `tf.TensorList*` to `tfl.custom_op` if they can all // be supported. bool legalize_custom_tensor_list_ops = false; // Whether to convert some tensor types to a lower precision if all values // within that tensor are within the range of the lower precision. This could // have side effects e.g. reduced flatbuffer size. Only certain type // conversions are supported. bool reduce_type_precision = false;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 19:05:30 UTC 2024 - 6.5K bytes - Viewed (0) -
tensorflow/c/eager/c_api_experimental.h
TF_Status* status, void* device_info); // Method to copy a tensor from the custom device to a target device. TFE_TensorHandle* (*copy_tensor_from_device)(TFE_Context* context, TFE_TensorHandle* tensor,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 21 22:37:46 UTC 2024 - 39.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/passes.h
// Legalize TensorList Ops iff all of them are supported. std::unique_ptr<OperationPass<ModuleOp>> CreateLegalizeTensorListPass(); // Reduce the type precision of some tensor types if all values within that // tensor are within the range of the reduced precision. std::unique_ptr<OperationPass<ModuleOp>> CreateReduceTypePrecisionPass(); // Convervatively pushes transposes through elementwise ops to prepare
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 07 21:29:34 UTC 2024 - 10.9K bytes - Viewed (0) -
tensorflow/c/experimental/grappler/grappler.h
// This may cause incorrectness in graph analyses, but is useful for simulation // or scheduling. // If include_input_tensor_values is true, the values of constant // tensors will included in the input properties. // If include_output_tensor_values is true, the values of constant tensors will // be included in the output properties. TF_CAPI_EXPORT extern void TF_InferStatically( TF_GraphProperties* graph_properties, TF_Bool assume_valid_feeds,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Aug 03 18:08:43 UTC 2022 - 12.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_ops_layout_helper.h
// Shuffle elements in the `attr` according to the permutation. Optional // `inner_size` allows to shuffle array attributes created from rank 2 tensors // on outer dimension only. ArrayAttr ShuffleArrayAttr(ArrayAttr attr, ArrayRef<int64_t> permutation, int inner_size = 1); // Shuffle ranked tensor dimensions according to the permutation. Type ShuffleRankedTensorType(Type type, ArrayRef<int64_t> permutation);
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jun 08 01:19:25 UTC 2023 - 5.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/replace_cast_hacks_with_tf_xla_ops.cc
} return true; } // Calculates other_tensor_zp * tensor for zero point offset calculation. // Things to do: // 1. Reduce the tensor (which is an input of XlaDotV2) with contracting // dimensions of XlaDotV2. // - The resultant dimension must match with XlaDotV2 resultant dimension // 2. Multiply it with zero point from the other tensor. // We decided to use tf.Einsum for step 1, since it would require transposes/
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 47.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_ops_a_m.cc
return op.emitOpError("requires min to be a 1d float tensor"); auto max = GetRankedTensorTypeForOperand(op.getMax()); if (max && !IsOfRankedFloatTensorType(max, 1)) return op.emitOpError("requires max to be a 1d float tensor"); Value inputs = op.getInputs(); if (!HasRankAtLeast(inputs, 1)) return op.emitError("requires inputs to be at least 1d float tensor"); int64_t num_bits = op.getNumBits();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 146.7K bytes - Viewed (0)