NNData¶

This message carries tensors and its data. NeuralNetwork node outputs NNData.

Creating NNData¶

You can also create this message on the host (example here) or Script node (example here), populate the tensor with the data, and send the message to the input of the NeuralNetwork node.

Reference¶

class depthai.NNData

getAllLayerNames(self: depthai.NNData) → list[str]

getAllLayers(self: depthai.NNData) → list[depthai.TensorInfo]

getData(self: object) → numpy.ndarray[numpy.uint8]

getFirstLayerFp16(self: depthai.NNData) → list[float]

getFirstLayerInt32(self: depthai.NNData) → list[int]

getFirstLayerUInt8(self: depthai.NNData) → list[int]

getLayer(self: depthai.NNData, name: str, tensor: depthai.TensorInfo) → bool

getLayerDatatype(self: depthai.NNData, name: str, datatype: depthai.TensorInfo.DataType) → bool

getLayerFp16(self: depthai.NNData, name: str) → list[float]

getLayerInt32(self: depthai.NNData, name: str) → list[int]

getLayerUInt8(self: depthai.NNData, name: str) → list[int]

getRaw(self: depthai.ADatatype) → depthai.RawBuffer

getSequenceNum(self: depthai.NNData) → int

getTimestamp(self: depthai.NNData) → datetime.timedelta

getTimestampDevice(self: depthai.NNData) → datetime.timedelta

hasLayer(self: depthai.NNData, name: str) → bool

setData(*args, **kwargs)

Overloaded function.

setData(self: depthai.Buffer, arg0: list[int]) -> None
setData(self: depthai.Buffer, arg0: numpy.ndarray[numpy.uint8]) -> None

setLayer(*args, **kwargs)

Overloaded function.

setLayer(self: depthai.NNData, name: str, data: numpy.ndarray[numpy.uint8]) -> None
setLayer(self: depthai.NNData, name: str, data: list[int]) -> depthai.NNData
setLayer(self: depthai.NNData, name: str, data: list[float]) -> depthai.NNData
setLayer(self: depthai.NNData, name: str, data: list[float]) -> depthai.NNData

setSequenceNum(self: depthai.NNData, arg0: int) → depthai.NNData

setTimestamp(self: depthai.NNData, arg0: datetime.timedelta) → depthai.NNData

setTimestampDevice(self: depthai.NNData, arg0: datetime.timedelta) → depthai.NNData

class dai::NNData : public dai::Buffer ¶

NNData message. Carries tensors and their metadata

Public Functions

NNData()¶: Construct NNData message.

NNData(std::shared_ptr<RawNNData> ptr)¶

~NNData() = default¶

NNData &setLayer(const std::string &name, std::vector<std::uint8_t> data)¶

Set a layer with datatype U8.

Parameters

name: Name of the layer
data: Data to store

NNData &setLayer(const std::string &name, const std::vector<int> &data)¶

Set a layer with datatype U8. Integers are cast to bytes.

Parameters

name: Name of the layer
data: Data to store

NNData &setLayer(const std::string &name, std::vector<float> data)¶

Set a layer with datatype FP16. Float values are converted to FP16.

Parameters

name: Name of the layer
data: Data to store

NNData &setLayer(const std::string &name, std::vector<double> data)¶

Set a layer with datatype FP16. Double values are converted to FP16.

Parameters

name: Name of the layer
data: Data to store

std::vector<std::string> getAllLayerNames() const¶

Return: Names of all layers added

std::vector<TensorInfo> getAllLayers() const¶

Return: All layers and their information

bool getLayer(const std::string &name, TensorInfo &tensor) const¶

Retrieve layers tensor information

Return

True if layer exists, false otherwise

Parameters

name: Name of the layer
[out] tensor: Outputs tensor information of that layer

bool hasLayer(const std::string &name) const¶

Checks if given layer exists

Return

True if layer exists, false otherwise

Parameters

name: Name of the layer

bool getLayerDatatype(const std::string &name, TensorInfo::DataType &datatype) const¶

Retrieve datatype of a layers tensor

Return

True if layer exists, false otherwise

Parameters

name: Name of the layer
[out] datatype: Datatype of layers tensor

std::vector<std::uint8_t> getLayerUInt8(const std::string &name) const¶

Convenience function to retrieve U8 data from layer

Return

U8 binary data

Parameters

name: Name of the layer

std::vector<float> getLayerFp16(const std::string &name) const¶

Convenience function to retrieve float values from layers FP16 tensor

Return

Float data

Parameters

name: Name of the layer

std::vector<std::int32_t> getLayerInt32(const std::string &name) const¶

Convenience function to retrieve INT32 values from layers tensor

Return

INT32 data

Parameters

name: Name of the layer

std::vector<std::uint8_t> getFirstLayerUInt8() const¶

Convenience function to retrieve U8 data from first layer

Return: U8 binary data

std::vector<float> getFirstLayerFp16() const¶

Convenience function to retrieve float values from first layers FP16 tensor

Return: Float data

std::vector<std::int32_t> getFirstLayerInt32() const¶

Convenience function to retrieve INT32 values from first layers tensor

Return: INT32 data

NNData &setTimestamp(std::chrono::time_point<std::chrono::steady_clock, std::chrono::steady_clock::duration> timestamp)¶: Sets image timestamp related to dai::Clock::now()

NNData &setTimestampDevice(std::chrono::time_point<std::chrono::steady_clock, std::chrono::steady_clock::duration> timestamp)¶: Sets image timestamp related to dai::Clock::now()

NNData &setSequenceNum(int64_t sequenceNum)¶: Retrieves image sequence number

Private Functions

std::shared_ptr<RawBuffer> serialize() const override¶

Private Members

RawNNData &rawNn¶

std::unordered_map<std::string, std::vector<std::uint8_t>> u8Data¶

std::unordered_map<std::string, std::vector<std::uint16_t>> fp16Data¶

Private Static Attributes

constexpr int DATA_ALIGNMENT = 64¶

Got questions?

Head over to Discussion Forum for technical support or any other questions you might have.