pynvvl:cupy的nvidia视频加载器(nvvl)的python包装器
pynvvl-cuda90的Python项目详细描述
PYNVVL
pynvvl是NVIDIA Video Loader (NVVL)的薄包装。此软件包允许您将视频Directoly加载到GPU内存中,并以零拷贝的CuPyndarrays方式访问它们。pynvvl的预构建二进制文件包括nvvl本身,因此不需要安装nvvl。
要求
- CUDA 8.0、9.0、9.1或9.2
- python 2.7.6+、3.4.7+、3.5.1+或3.6.0+
- CuPyv4.5.0
测试环境
- ubuntu 16.04
- python 2.7.6+、3.4.7+、3.5.1+和3.6.0+
- CUDA 8.0、9.0、9.1和9.2
安装预编译的二进制文件
请根据您的CUDA版本选择合适的软件包。
# [For CUDA 8.0] pip install pynvvl-cuda80 # [For CUDA 9.0] pip install pynvvl-cuda90 # [For CUDA 9.1] pip install pynvvl-cuda91 # [For CUDA 9.2] pip install pynvvl-cuda92
用法
importpynvvlimportmatplotlib.pyplotasplt# Create NVVLVideoLoader objectloader=pynvvl.NVVLVideoLoader(device_id=0,log_level='error')# Show the number of frames in the videon_frames=loader.frame_count('examples/sample.mp4')print('Number of frames:',n_frames)# Load a video and return it as a CuPy arrayvideo=loader.read_sequence('examples/sample.mp4',horiz_flip=True,scale_height=512,scale_width=512,crop_y=60,crop_height=385,crop_width=512,scale_method='Linear',normalized=True)print(video.shape)# => (91, 3, 385, 512): (n_frames, channels, height, width)print(video.dtype)# => float32# Get the first frame as numpy arrayframe=video[0].get()frame=frame.transpose(1,2,0)plt.imshow(frame)plt.savefig('examples/sample.png')
这段视频是来自时间瞬间数据集的flickr-2-6-3-3-5-2-7-6-5626335276_4.mp4
。
请注意,裁剪是在缩放后执行的。在上面的示例中,nvvl首先执行从256 x 256到512 x 512的缩放,然后裁剪区域[60:60+385,0:512]。有关转换选项的详细信息,请参见以下部分。
视频加载器选项
创建NVVLVideoLoader
对象时,请指定GPU设备ID。
您还可以使用参数log_level
为NVVLVideoLoader
的构造函数指定日志记录级别。
Wrapper of NVVL VideoLoader
Args:
device_id (int): Specify the device id used to load a video.
log_level (str): Logging level which should be either 'debug',
'info', 'warn', 'error', or 'none'.
Logs with levels >= log_level is shown. The default is 'warn'.
转换选项
pynvvl.NVVLVideoLoader.read_sequence
可以使用一些选项来指定颜色空间、值范围以及要对视频执行的转换。
Loads the video from disk and returns it as a CuPy ndarray.
Args:
filename (str): The path to the video.
frame (int): The initial frame number of the returned sequence.
Default is 0.
count (int): The number of frames of the returned sequence.
If it is None, whole frames of the video are loaded.
channels (int): The number of color channels of the video.
Default is 3.
scale_height (int): The height of the scaled video.
Note that scaling is performed before cropping.
If it is 0 no scaling is performed. Default is 0.
scale_width (int): The width of the scaled video.
Note that scaling is performed before cropping.
If it is 0, no scaling is performed. Default is 0.
crop_x (int): Location of the crop within the scaled frame.
Must be set such that crop_y + height <= original height.
Default is 0.
crop_y (int): Location of the crop within the scaled frame.
Must be set such that crop_x + width <= original height.
Default is 0.
crop_height (int): The height of cropped region of the video.
If it is None, no cropping is performed. Default is None.
crop_width (int): The width of cropped region of the video.
If it is None, no cropping is performed. Default is None.
scale_method (str): Scaling method. It should be either of
'Nearest' or 'Lienar'. Default is 'Linear'.
horiz_flip (bool): Whether horizontal flipping is performed or not.
Default is False.
normalized (bool): If it is True, the values of returned video is
normalized into [0, 1], otherwise the value range is [0, 255].
Default is False.
color_space (str): The color space of the values of returned video.
It should be either 'RGB' or 'YCbCr'. Default is 'RGB'.
chroma_up_method (str): How the chroma channels are upscaled from
yuv 4:2:0 to 4:4:4. It should be 'Linear' currently.
out (cupy.ndarray): Alternate output array where place the result.
It must have the same shape and the dtype as the expected
output, and its order must be C-contiguous.
如何构建
使用Docker构建轮子:
要求:
- 码头工人
- NVIDIA Docker(v1/v2)
bash docker/build_wheels.sh
设置不带Docker的开发环境:
setup.py
脚本搜索必要的库。
要求:以下库在LIBRARY_PATH
中可用。
- libnvvl.so
- libavformat.so.57
- libavfilter.so.6
- libavcodec.so.57
- libavutil.so.55
您可以在nvvl
存储库中构建libnvvl.so
。按照说明操作
在nvvl
库中。build
目录必须在LIBRARY_PATH
中。
其他三个库在ubuntu 16.04中作为包提供。
它们安装在/usr/lib/x86_64-linux-gnu
下,因此它们也必须在LIBRARY_PATH
中。
python setup.py develop
python setup.py bdist_wheel