io.hydrosphere.serving.tensorflow.tensor
Shape of the tensor.
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.
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.
DT_HALF. Note that since protobuf has no int16 type, we'll have some pointless zero padding for each value here.
DT_FLOAT.
DT_DOUBLE.
DT_INT32, DT_INT16, DT_INT8, DT_UINT8.
DT_STRING
DT_COMPLEX64. scomplex_val(2*i) and scomplex_val(2*i+1) are real and imaginary parts of i-th single precision complex.
DT_INT64
DT_BOOL
DT_COMPLEX128. dcomplex_val(2*i) and dcomplex_val(2*i+1) are real and imaginary parts of i-th double precision complex.
DT_VARIANT
DT_UINT32
DT_UINT64
Hydroserving
DT_BOOL
DT_COMPLEX128.
DT_COMPLEX128. dcomplex_val(2*i) and dcomplex_val(2*i+1) are real and imaginary parts of i-th double precision complex.
DT_DOUBLE.
DT_FLOAT.
DT_HALF.
DT_HALF. Note that since protobuf has no int16 type, we'll have some pointless zero padding for each value here.
DT_INT64
DT_INT32, DT_INT16, DT_INT8, DT_UINT8.
Hydroserving
DT_COMPLEX64.
DT_COMPLEX64. scomplex_val(2*i) and scomplex_val(2*i+1) are real and imaginary parts of i-th single precision complex.
DT_STRING
Serialized raw tensor content from either Tensor::AsProtoTensorContent or memcpy in tensorflow::grpc::EncodeTensorToByteBuffer.
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.
Shape of the tensor.
DT_UINT32
DT_UINT64
DT_VARIANT
Version number.
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.
(Since version 0.6.0) Use toPMessage
(Since version 0.6.0) Use getField that accepts a ScalaPB descriptor and returns PValue
Protocol buffer representing a tensor.
Shape of the tensor.
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.
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.
DT_HALF. Note that since protobuf has no int16 type, we'll have some pointless zero padding for each value here.
DT_FLOAT.
DT_DOUBLE.
DT_INT32, DT_INT16, DT_INT8, DT_UINT8.
DT_STRING
DT_COMPLEX64. scomplex_val(2*i) and scomplex_val(2*i+1) are real and imaginary parts of i-th single precision complex.
DT_INT64
DT_BOOL
DT_COMPLEX128. dcomplex_val(2*i) and dcomplex_val(2*i+1) are real and imaginary parts of i-th double precision complex.
DT_VARIANT
DT_UINT32
DT_UINT64
Hydroserving