api/pkg/apis/tfserving/v1/tensor.proto

113 lines
3.9 KiB
Protocol Buffer

/*
* Copyright 2023 The Dragonfly Authors
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
syntax = "proto3";
package tfserving.v1;
import "pkg/apis/tfserving/v1/resource_handle.proto";
import "pkg/apis/tfserving/v1/tensor_shape.proto";
import "pkg/apis/tfserving/v1/types.proto";
option go_package = "d7y.io/api/pkg/apis/tfserving/v1;tfserving";
// Protocol buffer representing a tensor.
message TensorProto {
tfserving.v1.DataType dtype = 1;
// Shape of the tensor. TODO(touts): sort out the 0-rank issues.
tfserving.v1.TensorShapeProto tensor_shape = 2;
// Only one of the representations below is set, one of "tensor_contents" and
// the "xxx_val" attributes. We are not using oneof because as oneofs cannot
// contain repeated fields it would require another extra set of messages.
// Version number.
//
// In version 0, if the "repeated xxx" representations contain only one
// element, that element is repeated to fill the shape. This makes it easy
// to represent a constant Tensor with a single value.
int32 version_number = 3;
// Serialized raw tensor content from either Tensor::AsProtoTensorContent or
// memcpy in tensorflow::grpc::EncodeTensorToByteBuffer. This representation
// can be used for all tensor types. The purpose of this representation is to
// reduce serialization overhead during RPC call by avoiding serialization of
// many repeated small items.
bytes tensor_content = 4;
// Type specific representations that make it easy to create tensor protos in
// all languages. Only the representation corresponding to "dtype" can
// be set. The values hold the flattened representation of the tensor in
// row major order.
// DT_HALF, DT_BFLOAT16. Note that since protobuf has no int16 type, we'll
// have some pointless zero padding for each value here.
repeated int32 half_val = 13 [packed = true];
// DT_FLOAT.
repeated float float_val = 5 [packed = true];
// DT_DOUBLE.
repeated double double_val = 6 [packed = true];
// DT_INT32, DT_INT16, DT_UINT16, DT_INT8, DT_UINT8.
repeated int32 int_val = 7 [packed = true];
// DT_STRING
repeated bytes string_val = 8;
// DT_COMPLEX64. scomplex_val(2*i) and scomplex_val(2*i+1) are real
// and imaginary parts of i-th single precision complex.
repeated float scomplex_val = 9 [packed = true];
// DT_INT64
repeated int64 int64_val = 10 [packed = true];
// DT_BOOL
repeated bool bool_val = 11 [packed = true];
// DT_COMPLEX128. dcomplex_val(2*i) and dcomplex_val(2*i+1) are real
// and imaginary parts of i-th double precision complex.
repeated double dcomplex_val = 12 [packed = true];
// DT_RESOURCE
repeated tfserving.v1.ResourceHandleProto resource_handle_val = 14;
// DT_VARIANT
repeated VariantTensorDataProto variant_val = 15;
// DT_UINT32
repeated uint32 uint32_val = 16 [packed = true];
// DT_UINT64
repeated uint64 uint64_val = 17 [packed = true];
// DT_FLOAT8_*, use variable-sized set of bytes
// (i.e. the equivalent of repeated uint8, if such a thing existed).
bytes float8_val = 18;
}
// Protocol buffer representing the serialization format of DT_VARIANT tensors.
message VariantTensorDataProto {
// Name of the type of objects being serialized.
string type_name = 1;
// Portions of the object that are not Tensors.
bytes metadata = 2;
// Tensors contained within objects being serialized.
repeated tfserving.v1.TensorProto tensors = 3;
}