neuromorphic_drivers 是一个用于与USB神经形态设备交互的库。驱动程序从头开始编写，考虑到可移植性和性能。

• 支持设备和功能
• Python
  • 入门指南
  • 设备配置
  • 速率限制器
  • 原始模式
  • 其他开放选项
  • 更多示例
  • 贡献
• Rust
  • 文档
  • UDEV规则
  • 贡献
• 性能
  • 事件速率
  • 直接内存访问

支持设备和功能

此表列出了该库支持的特性。一些设备支持未列出的特性或标记为“未添加”的特性，这些特性尚未添加到 neuromorphic_drivers。

Python

入门指南

pip install neuromorphic_drivers

在Linux上，安装包后运行以下命令以安装UDEV规则。

neuromorphic-drivers-install-udev-rules

以下脚本从连接的设备读取数据。

import neuromorphic_drivers as nd

nd.print_device_list()  # print a table that lists connected devices

with nd.open() as device:
    for status, packet in device:
        if "dvs_events" in packet:
            # packet["dvs_events"] is a structured numpy array
            # with dtype [("t", "<u8"), ("x", "<u2"), ("y", "<u2"), ("on", "?")])
            pass
        if "trigger_events" in packet:
            # packet["trigger_events"] is a structured numpy array
            # with dtype [("t", "<u8"), ("id, "<u1"), ("rising", "?")])
            pass

数据包中的键取决于设备，并且仅在关联数组非空时存在。数据包包含可变数量的事件（通常为几千到几百万），覆盖可变的时间量（通常为几十微秒到几毫秒）。

设备配置

配置（针对每个设备特定）定义了所有设备参数，从偏置到感兴趣的区域。它可以在打开设备时指定，并且可以在任何时候更新。设备 d 的默认配置在 python/neuromorphic_drivers/generated/devices/d.py 中定义。

import neuromorphic_drivers as nd

configuration = nd.prophesee_evk4.Configuration(
    biases=nd.prophesee_evk4.Biases(
        diff_off=170,
        diff_on=130,
    )
)

with nd.open(configuration=configuration) as device:
    for status, packet in device:
        ...
        if not_sensitive_enough:
            configuration.biases.diff_on -= 10
            configuration.biases.diff_off -= 10
            device.update_configuration(configuration)

nd.open 可打开任何支持的设备。但是，如果指定了配置，则仅考虑匹配的设备。向 update_configuration 传递错误的配置类型会引发错误。

速率限制器

Prophesee的EVK4具有硬件事件速率限制器，当传感器每秒生成的数据超过指定数量时，会随机丢弃事件。限制器有两个参数。reference_period_us定义了计数周期（最大200µs）。maximum_events_per_period定义了每个周期内事件的数量，超过这个数量限制器会启动。实际限制是maximum_events_per_period / reference_period_us事件/µs。

import neuromorphic_drivers as nd

configuration = nd.prophesee_evk4.Configuration(
    rate_limiter=nd.prophesee_evk4.RateLimiter(
        reference_period_us=200,
        maximum_events_per_period=4000,
    )
)

with nd.open(configuration=configuration) as device:
    ...

原始模式

如果数据速率高，将原始USB数据转换为事件可能是一个昂贵的操作。原始模式跳过解析，如果只是想将数据存储到文件以供离线处理，则可能很有用。

import neuromorphic_drivers as nd

with nd.open(raw=True) as device:
    for status, packet in device:
        # in raw mode, packet is a "bytes" object

其他开放选项

def open(
    # initial device configuration
    configuration: typing.Optional[Configuration] = None,

    # timeout for each iteration (for status, packet in device)
    # By default, the iterator blocks until data is available.
    # In some cases (other time-driven calculations, graphics...),
    # it can be desirable to run an iteration of the loop even if no data is available.
    # If iterator_timeout is not None, packet may be None.
    iterator_timeout: typing.Optional[float] = None,

    # whether to skip data parsing
    raw: bool = False,

    # device serial number, None selects the first available device.
    # Use nd.list_devices() to get a list of connected devices and their serials.
    serial: typing.Optional[str] = None,

    # USB software ring configuration, None falls back to default.
    usb_configuration: typing.Optional[UsbConfiguration] = None,

    # maximum number of raw USB packets merged to create a packet returned by the iterator.
    # Under typical conditions, each iterator packet is built from one USB packet.
    # However, if more than one USB packet has already been received,
    # the library builds the iterator packet by merging the USB packets,
    # to reduce the number of GIL (Global Interpreter Lock) operations.
    # While merging speeds up processing in such cases, it can lead to large latency spikes if too many packets are merged at once.
    # iterator_maximum_raw_packets limits the number of packets that are merged, even if more USB packets have been received.
    # The remaning USB packets are not dropped but simply returned on the next iteration(s).
    iterator_maximum_raw_packets: int = 64,
): ...

USB配置的字段在设备间是相同的，但默认值取决于设备。以下值适用于Prophesee EVK4。

@dataclasses.dataclass
class UsbConfiguration:
    buffer_length: serde.type.uint64 = 131072 # size of each buffer in the ring, in bytes
    ring_length: serde.type.uint64 = 4096 # number of buffers in the ring, the total size is ring_length * buffer_length
    transfer_queue_length: serde.type.uint64 = 32 # number of libusb transfers submitted in parallel
    allow_dma: bool = False # whether to enable Direct Memory Access

更多示例

有关不同用法示例，请参阅python/examples。

python/examples/any_display.py实现了一个使用GPU计算指数衰减的实时事件查看器。它需要vispy和glfw（pip install vispy glfw pyopengl）。

python/examples/evk4_plot_hot_pixels生成图表并需要Plotly（pip install plotly pandas kaleido）。

贡献

本地构建（首次运行）。

cd python
python3 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip
pip install maturin numpy
maturin develop  # or maturin develop --release to build with optimizations

本地构建（后续运行）。

cd python
source .venv/bin/activate
maturin develop  # or maturin develop --release to build with optimizations

在推送新代码之前，运行以下命令以进行代码审查和格式化。

cd python
isort .; black .; pyright .

python/python/neuromorphic_drivers/generated中的文件由构建脚本（python/build.rs）生成，不应直接修改。这些文件包含在本存储库中，用于文档目的。

当同时修改Rust库和Python包装器时，将neuromorphic-drivers = "x.y"更改为neuromorphic-drivers = {path = "../drivers"}以使用最新的Rust代码版本。

cd drivers
cargo test --release read -- --nocapture

cargo publish -p neuromorphic-types
cargo publish -p neuromorphic-drivers