--- title: "GET /transform-output" method: GET path: "/transform-output" tags: ["Internal"] --- # GET /transform-output `GET /transform-output` ## Query parameters - `json` SeldonMessage, required - `binData` string, byte - `data` DefaultData - `names` string[] - `ndarry` AnyValue[] - unknown - `tensor` Tensor - `shape` integer[] - `values` number[] - `tftensor` TensorflowTensorProto — Protocol buffer representing a tensor. - `bool_val` boolean[] - `dcomplex_val` number[] — DT_COMPLEX128. dcomplex_val(2*i) and dcomplex_val(2*i+1) are real and imaginary parts of i-th double precision complex. - `double_val` number[] — DT_DOUBLE. - `dtype` 'DT_INVALID' | 'DT_FLOAT' | 'DT_DOUBLE' | 'DT_INT32' | 'DT_UINT8' | 'DT_INT16' | 'DT_INT8' | 'DT_STRING' | 'DT_COMPLEX64' | 'DT_INT64' | 'DT_BOOL' | 'DT_QINT8' | 'DT_QUINT8' | 'DT_QINT32' | 'DT_BFLOAT16' | 'DT_QINT16' | 'DT_QUINT16' | 'DT_UINT16' | 'DT_COMPLEX128' | 'DT_HALF' | 'DT_RESOURCE' | 'DT_VARIANT' | 'DT_UINT32' | 'DT_UINT64' | 'DT_FLOAT_REF' | 'DT_DOUBLE_REF' | 'DT_INT32_REF' | 'DT_UINT8_REF' | 'DT_INT16_REF' | 'DT_INT8_REF' | 'DT_STRING_REF' | 'DT_COMPLEX64_REF' | 'DT_INT64_REF' | 'DT_BOOL_REF' | 'DT_QINT8_REF' | 'DT_QUINT8_REF' | 'DT_QINT32_REF' | 'DT_BFLOAT16_REF' | 'DT_QINT16_REF' | 'DT_QUINT16_REF' | 'DT_UINT16_REF' | 'DT_COMPLEX128_REF' | 'DT_HALF_REF' | 'DT_RESOURCE_REF' | 'DT_VARIANT_REF' | 'DT_UINT32_REF' | 'DT_UINT64_REF' — - DT_INVALID: Not a legal value for DataType. Used to indicate a DataType field has not been set. - DT_FLOAT: Data types that all computation devices are expected to be capable to support. - DT_FLOAT_REF: Do not use! These are only for parameters. Every enum above should have a corresponding value below (verified by types_test). - `float_val` number[] — DT_FLOAT. - `half_val` integer[] — DT_HALF, DT_BFLOAT16. Note that since protobuf has no int16 type, we'll have some pointless zero padding for each value here. - `int64_val` string[] - `int_val` integer[] — DT_INT32, DT_INT16, DT_INT8, DT_UINT8. - `resource_handle_val` TensorflowResourceHandleProto[] - `container` string — Container in which this resource is placed. - `device` string — Unique name for the device containing the resource. - `hash_code` string, uint64 — Hash code for the type of the resource. Is only valid in the same device and in the same execution. - `maybe_type_name` string — For debug-only, the name of the type pointed to by this handle, if available. - `name` string — Unique name of this resource. - `scomplex_val` number[] — DT_COMPLEX64. scomplex_val(2*i) and scomplex_val(2*i+1) are real and imaginary parts of i-th single precision complex. - `string_val` string[] - `tensor_content` string, byte — 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. - `tensor_shape` TensorflowTensorShapeProto — Dimensions of a tensor. - `dim` TensorShapeProtoDim[] — Dimensions of the tensor, such as {"input", 30}, {"output", 40} for a 30 x 40 2D tensor. If an entry has size -1, this corresponds to a dimension of unknown size. The names are optional. The order of entries in "dim" matters: It indicates the layout of the values in the tensor in-memory representation. The first entry in "dim" is the outermost dimension used to layout the values, the last entry is the innermost dimension. This matches the in-memory layout of RowMajor Eigen tensors. If "dim.size()" > 0, "unknown_rank" must be false. - `name` string — Optional name of the tensor dimension. - `size` string, int64 — Size of the tensor in that dimension. This value must be >= -1, but values of -1 are reserved for "unknown" shapes (values of -1 mean "unknown" dimension). Certain wrappers that work with TensorShapeProto may fail at runtime when deserializing a TensorShapeProto containing a dim value of -1. - `unknown_rank` boolean — If true, the number of dimensions in the shape is unknown. If true, "dim.size()" must be 0. - `uint32_val` integer[] - `uint64_val` string[] - `variant_val` TensorflowVariantTensorDataProto[] - `metadata` string, byte — Portions of the object that are not Tensors. - `tensors` TensorflowTensorProto[] — Tensors contained within objects being serialized. - `type_name` string — Name of the type of objects being serialized. - `version_number` integer — 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. - `meta` Meta - `metrics` Metric[] - `key` string - `type` 'COUNTER' | 'GAUGE' | 'TIMER' - `value` number, float - `puid` string - `requestPath` object - `routing` object - `tags` object - `status` Status - `code` integer - `info` string - `reason` string - `status` 'SUCCESS' | 'FAILURE' - `strData` string ## Response `200` A successful response. - SeldonMessage - `binData` string, byte - `data` DefaultData - `names` string[] - `ndarry` AnyValue[] - unknown - `tensor` Tensor - `shape` integer[] - `values` number[] - `tftensor` TensorflowTensorProto — Protocol buffer representing a tensor. - `bool_val` boolean[] - `dcomplex_val` number[] — DT_COMPLEX128. dcomplex_val(2*i) and dcomplex_val(2*i+1) are real and imaginary parts of i-th double precision complex. - `double_val` number[] — DT_DOUBLE. - `dtype` 'DT_INVALID' | 'DT_FLOAT' | 'DT_DOUBLE' | 'DT_INT32' | 'DT_UINT8' | 'DT_INT16' | 'DT_INT8' | 'DT_STRING' | 'DT_COMPLEX64' | 'DT_INT64' | 'DT_BOOL' | 'DT_QINT8' | 'DT_QUINT8' | 'DT_QINT32' | 'DT_BFLOAT16' | 'DT_QINT16' | 'DT_QUINT16' | 'DT_UINT16' | 'DT_COMPLEX128' | 'DT_HALF' | 'DT_RESOURCE' | 'DT_VARIANT' | 'DT_UINT32' | 'DT_UINT64' | 'DT_FLOAT_REF' | 'DT_DOUBLE_REF' | 'DT_INT32_REF' | 'DT_UINT8_REF' | 'DT_INT16_REF' | 'DT_INT8_REF' | 'DT_STRING_REF' | 'DT_COMPLEX64_REF' | 'DT_INT64_REF' | 'DT_BOOL_REF' | 'DT_QINT8_REF' | 'DT_QUINT8_REF' | 'DT_QINT32_REF' | 'DT_BFLOAT16_REF' | 'DT_QINT16_REF' | 'DT_QUINT16_REF' | 'DT_UINT16_REF' | 'DT_COMPLEX128_REF' | 'DT_HALF_REF' | 'DT_RESOURCE_REF' | 'DT_VARIANT_REF' | 'DT_UINT32_REF' | 'DT_UINT64_REF' — - DT_INVALID: Not a legal value for DataType. Used to indicate a DataType field has not been set. - DT_FLOAT: Data types that all computation devices are expected to be capable to support. - DT_FLOAT_REF: Do not use! These are only for parameters. Every enum above should have a corresponding value below (verified by types_test). - `float_val` number[] — DT_FLOAT. - `half_val` integer[] — DT_HALF, DT_BFLOAT16. Note that since protobuf has no int16 type, we'll have some pointless zero padding for each value here. - `int64_val` string[] - `int_val` integer[] — DT_INT32, DT_INT16, DT_INT8, DT_UINT8. - `resource_handle_val` TensorflowResourceHandleProto[] - `container` string — Container in which this resource is placed. - `device` string — Unique name for the device containing the resource. - `hash_code` string, uint64 — Hash code for the type of the resource. Is only valid in the same device and in the same execution. - `maybe_type_name` string — For debug-only, the name of the type pointed to by this handle, if available. - `name` string — Unique name of this resource. - `scomplex_val` number[] — DT_COMPLEX64. scomplex_val(2*i) and scomplex_val(2*i+1) are real and imaginary parts of i-th single precision complex. - `string_val` string[] - `tensor_content` string, byte — 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. - `tensor_shape` TensorflowTensorShapeProto — Dimensions of a tensor. - `dim` TensorShapeProtoDim[] — Dimensions of the tensor, such as {"input", 30}, {"output", 40} for a 30 x 40 2D tensor. If an entry has size -1, this corresponds to a dimension of unknown size. The names are optional. The order of entries in "dim" matters: It indicates the layout of the values in the tensor in-memory representation. The first entry in "dim" is the outermost dimension used to layout the values, the last entry is the innermost dimension. This matches the in-memory layout of RowMajor Eigen tensors. If "dim.size()" > 0, "unknown_rank" must be false. - `name` string — Optional name of the tensor dimension. - `size` string, int64 — Size of the tensor in that dimension. This value must be >= -1, but values of -1 are reserved for "unknown" shapes (values of -1 mean "unknown" dimension). Certain wrappers that work with TensorShapeProto may fail at runtime when deserializing a TensorShapeProto containing a dim value of -1. - `unknown_rank` boolean — If true, the number of dimensions in the shape is unknown. If true, "dim.size()" must be 0. - `uint32_val` integer[] - `uint64_val` string[] - `variant_val` TensorflowVariantTensorDataProto[] - `metadata` string, byte — Portions of the object that are not Tensors. - `tensors` TensorflowTensorProto[] — Tensors contained within objects being serialized. - `type_name` string — Name of the type of objects being serialized. - `version_number` integer — 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. - `meta` Meta - `metrics` Metric[] - `key` string - `type` 'COUNTER' | 'GAUGE' | 'TIMER' - `value` number, float - `puid` string - `requestPath` object - `routing` object - `tags` object - `status` Status - `code` integer - `info` string - `reason` string - `status` 'SUCCESS' | 'FAILURE' - `strData` string --- [API](https://skmtc.net/seldon/apis/core.md) · [All operations](https://skmtc.net/seldon/apis/core/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/seldon/core/versions/0bdac47ceebf/schema)