angular做的网站大全,株洲网站建设服务公司,抖音自动推广引流app,做adsense对网站有什么要求Linux 36.3 JetPack v6.0jetson-inference之图像分类 1. 源由2. imagenet2.1 命令选项2.2 下载模型2.3 操作示例2.3.1 单张照片2.3.2 视频 3. 代码3.1 Python3.2 C 4. 参考资料5. 补充5.1 第一次运行模型本地适应初始化5.2 samba软连接 1. 源由
从应用角度来说#xff0c;图… Linux 36.3 JetPack v6.0jetson-inference之图像分类 1. 源由2. imagenet2.1 命令选项2.2 下载模型2.3 操作示例2.3.1 单张照片2.3.2 视频 3. 代码3.1 Python3.2 C 4. 参考资料5. 补充5.1 第一次运行模型本地适应初始化5.2 samba软连接 1. 源由
从应用角度来说图像分类是计算机视觉里面最基本的一个操作。
2. imagenet
imageNet对象接受输入图像并输出每个类别的概率。GoogleNet和ResNet-18模型在构建过程中自动下载这些模型已在包含1000个物体的ImageNet ILSVRC数据集上进行了训练。
2.1 命令选项
$ imagenet --help
usage: imagenet [--help] [--networkNETWORK] ...input_URI [output_URI]Classify a video/image stream using an image recognition DNN.
See below for additional arguments that may not be shown above.optional arguments:--help show this help message and exit--networkNETWORK pre-trained model to load (see below for options)--topKN show the topK number of class predictions (default: 1)
positional arguments:input_URI resource URI of input stream (see videoSource below)output_URI resource URI of output stream (see videoOutput below)imageNet arguments:--networkNETWORK pre-trained model to load, one of the following:* alexnet* googlenet (default)* googlenet-12* resnet-18* resnet-50* resnet-101* resnet-152* vgg-16* vgg-19* inception-v4--modelMODEL path to custom model to load (caffemodel, uff, or onnx)--prototxtPROTOTXT path to custom prototxt to load (for .caffemodel only)--labelsLABELS path to text file containing the labels for each class--input-blobINPUT name of the input layer (default is data)--output-blobOUTPUT name of the output layer (default is prob)--thresholdCONF minimum confidence threshold for classification (default is 0.01)--smoothingWEIGHT weight between [0,1] or number of frames (disabled by default)--profile enable layer profiling in TensorRTvideoSource arguments:input resource URI of the input stream, for example:* /dev/video0 (V4L2 camera #0)* csi://0 (MIPI CSI camera #0)* rtp://:1234 (RTP stream)* rtsp://user:passip:1234 (RTSP stream)* webrtc://:1234/my_stream (WebRTC stream)* file://my_image.jpg (image file)* file://my_video.mp4 (video file)* file://my_directory/ (directory of images)--input-widthWIDTH explicitly request a width of the stream (optional)--input-heightHEIGHT explicitly request a height of the stream (optional)--input-rateRATE explicitly request a framerate of the stream (optional)--input-saveFILE path to video file for saving the input stream to disk--input-codecCODEC RTP requires the codec to be set, one of these:* h264, h265* vp8, vp9* mpeg2, mpeg4* mjpeg--input-decoderTYPE the decoder engine to use, one of these:* cpu* omx (aarch64/JetPack4 only)* v4l2 (aarch64/JetPack5 only)--input-flipFLIP flip method to apply to input:* none (default)* counterclockwise* rotate-180* clockwise* horizontal* vertical* upper-right-diagonal* upper-left-diagonal--input-loopLOOP for file-based inputs, the number of loops to run:* -1 loop forever* 0 dont loop (default)* 0 set number of loopsvideoOutput arguments:output resource URI of the output stream, for example:* file://my_image.jpg (image file)* file://my_video.mp4 (video file)* file://my_directory/ (directory of images)* rtp://remote-ip:1234 (RTP stream)* rtsp://:8554/my_stream (RTSP stream)* webrtc://:1234/my_stream (WebRTC stream)* display://0 (OpenGL window)--output-codecCODEC desired codec for compressed output streams:* h264 (default), h265* vp8, vp9* mpeg2, mpeg4* mjpeg--output-encoderTYPE the encoder engine to use, one of these:* cpu* omx (aarch64/JetPack4 only)* v4l2 (aarch64/JetPack5 only)--output-saveFILE path to a video file for saving the compressed streamto disk, in addition to the primary output above--bitrateBITRATE desired target VBR bitrate for compressed streams,in bits per second. The default is 4000000 (4 Mbps)--headless dont create a default OpenGL GUI windowlogging arguments:--log-fileFILE output destination file (default is stdout)--log-levelLEVEL message output threshold, one of the following:* silent* error* warning* success* info* verbose (default)* debug--verbose enable verbose logging (same as --log-levelverbose)--debug enable debug logging (same as --log-leveldebug)注关于照片、视频等基本操作详见 《Linux 36.3 JetPack v6.0jetson-inference之视频操作》
2.2 下载模型
两种方式
创建imageNet对象时初始化会自动下载通过手动将模型文件放置到data/networks/目录下
国内由于“墙”的存在对于我们这种处于起飞阶段的菜鸟来说就是“障碍”。有条件的朋友可以参考《apt-get通过代理更新系统》进行设置网络。
不过NVIDIA还是很热心的帮助我们做了“Work around”所有的模型都已经预先存放在中国大陆能访问的位置Github - model-mirror-190618 --networkNETWORK pre-trained model to load, one of the following:* alexnet* googlenet (default)* googlenet-12* resnet-18* resnet-50* resnet-101* resnet-152* vgg-16* vgg-19* inception-v4--modelMODEL path to custom model to load (caffemodel, uff, or onnx)根据以上Model方面信息该命令支持
alexnetgooglenet (default)googlenet-12resnet-18resnet-50resnet-101resnet-152vgg-16vgg-19inception-v4支持定制模型(需要用到通用的模型文件caffemodel, uff, or onnx)
作为示例就下载一个googlenet (default)模型
$ mkdir model-mirror-190618
$ cd model-mirror-190618
$ wget https://github.com/dusty-nv/jetson-inference/releases/download/model-mirror-190618/GoogleNet.tar.gz
$ mkdir -p ../data/networks/Googlenet
$ tar -zxvf GoogleNet.tar.gz -C ../data/networks/Googlenet
$ cd ..注这个模型文件下载要注意将解压缩文件放置到Googlenet目录下。
2.3 操作示例
它加载图像或多张图像使用TensorRT和imageNet类进行推理然后叠加分类结果并保存输出图像。该项目附带了供您使用的示例图像这些图像位于images/目录下。
What’s wrong with imagenet, continous printf?
$ cd build/aarch64/bin/2.3.1 单张照片
# C
$ ./imagenet images/orange_0.jpg images/test/output_imagenet_cpp.jpg# Python
$ ./imagenet.py images/strawberry_0.jpg images/test/output_imagenet_python.jpg2.3.2 视频
# Download test video (thanks to jell.yfish.us)
$ wget https://nvidia.box.com/shared/static/tlswont1jnyu3ix2tbf7utaekpzcx4rc.mkv -O jellyfish.mkv# C
$ ./imagenet --networkresnet-18 ../../../jellyfish.mkv images/test/output_imagenet_jellyfish_cpp.mkv# Python
$ ./imagenet.py --networkresnet-18 ../../../jellyfish.mkv images/test/output_imagenet_jellyfish_python.mkv这里视频就放一份了理论上将既然有概率性的问题求解方式不同时间运算的结果可能会有差异。但是基于这个模型计算机没有记忆所以理论上是同一个概率。
那么问题来了照片的CPP和Python两次运算概率确是是不一样的。这是什么原因呢 output_imagenet_jellyfish_cpp 3. 代码
3.1 Python
Import statements
├── sys
├── argparse
├── jetson_inference
│ └── imageNet
└── jetson_utils├── videoSource├── videoOutput├── cudaFont└── LogCommand line parsing
├── Create ArgumentParser
│ ├── description
│ ├── formatter_class
│ └── epilog
├── Add arguments
│ ├── input
│ ├── output
│ ├── --network
│ └── --topK
└── Parse arguments├── try│ └── args parser.parse_known_args()[0]└── except├── print()├── parser.print_help()└── sys.exit(0)Load the recognition network
└── net imageNet(args.network, sys.argv)Optional hard-coded model loading (commented out)
└── net imageNet(modelmodel/resnet18.onnx, labelsmodel/labels.txt, input_blobinput_0, output_bloboutput_0)Create video sources outputs
├── input videoSource(args.input, argvsys.argv)
├── output videoOutput(args.output, argvsys.argv)
└── font cudaFont()Process frames until EOS or user exits
└── while True├── Capture the next image│ ├── img input.Capture()│ └── if img is None│ └── continue├── Classify the image and get the topK predictions│ └── predictions net.Classify(img, topKargs.topK)├── Draw predicted class labels│ └── for n, (classID, confidence) in enumerate(predictions)│ ├── classLabel net.GetClassLabel(classID)│ ├── confidence * 100.0│ ├── print(fimagenet: {confidence:05.2f}% class #{classID} ({classLabel}))│ └── font.OverlayText(img, textf{confidence:05.2f}% {classLabel}, │ x5, y5 n * (font.GetSize() 5),│ colorfont.White, backgroundfont.Gray40)├── Render the image│ └── output.Render(img)├── Update the title bar│ └── output.SetStatus({:s} | Network {:.0f} FPS.format(net.GetNetworkName(), net.GetNetworkFPS()))├── Print out performance info│ └── net.PrintProfilerTimes()└── Exit on input/output EOS└── if not input.IsStreaming() or not output.IsStreaming()└── break3.2 C
#include statements
├── videoSource.h
├── videoOutput.h
├── cudaFont.h
├── imageNet.h
└── signal.hGlobal variables
└── bool signal_recieved false;Function definitions
├── void sig_handler(int signo)
│ └── if (signo SIGINT)
│ ├── LogVerbose(received SIGINT\n);
│ └── signal_recieved true;
└── int usage()├── printf(usage: imagenet [--help] [--networkNETWORK] ...\n);├── printf( input_URI [output_URI]\n\n);├── printf(Classify a video/image stream using an image recognition DNN.\n);├── printf(See below for additional arguments that may not be shown above.\n\n);├── printf(optional arguments:\n);├── printf( --help show this help message and exit\n);├── printf( --networkNETWORK pre-trained model to load (see below for options)\n);├── printf( --topKN show the topK number of class predictions (default: 1)\n);├── printf(positional arguments:\n);├── printf( input_URI resource URI of input stream (see videoSource below)\n);├── printf( output_URI resource URI of output stream (see videoOutput below)\n\n);├── printf(%s, imageNet::Usage());├── printf(%s, videoSource::Usage());├── printf(%s, videoOutput::Usage());└── printf(%s, Log::Usage());main function
├── Parse command line
│ ├── commandLine cmdLine(argc, argv);
│ └── if (cmdLine.GetFlag(help))
│ └── return usage();
├── Attach signal handler
│ └── if (signal(SIGINT, sig_handler) SIG_ERR)
│ └── LogError(cant catch SIGINT\n);
├── Create input stream
│ ├── videoSource* input videoSource::Create(cmdLine, ARG_POSITION(0));
│ └── if (!input)
│ ├── LogError(imagenet: failed to create input stream\n);
│ └── return 1;
├── Create output stream
│ ├── videoOutput* output videoOutput::Create(cmdLine, ARG_POSITION(1));
│ └── if (!output)
│ ├── LogError(imagenet: failed to create output stream\n);
│ └── return 1;
├── Create font for image overlay
│ ├── cudaFont* font cudaFont::Create();
│ └── if (!font)
│ ├── LogError(imagenet: failed to load font for overlay\n);
│ └── return 1;
├── Create recognition network
│ ├── imageNet* net imageNet::Create(cmdLine);
│ └── if (!net)
│ ├── LogError(imagenet: failed to initialize imageNet\n);
│ └── return 1;
│ ├── const int topK cmdLine.GetInt(topK, 1); // default top result
├── Processing loop
│ └── while (!signal_recieved)
│ ├── uchar3* image NULL;
│ ├── int status 0;
│ ├── if (!input-Capture(image, status))
│ │ └── if (status videoSource::TIMEOUT)
│ │ └── continue;
│ │ └── break; // EOS
│ ├── imageNet::Classifications classifications; // classID, confidence
│ ├── if (net-Classify(image, input-GetWidth(), input-GetHeight(), classifications, topK) 0)
│ │ └── continue;
│ ├── for (uint32_t n0; n classifications.size(); n)
│ │ ├── const uint32_t classID classifications[n].first;
│ │ ├── const char* classLabel net-GetClassLabel(classID);
│ │ ├── const float confidence classifications[n].second * 100.0f;
│ │ ├── LogVerbose(imagenet: %2.5f%% class #%i (%s)\n, confidence, classID, classLabel);
│ │ ├── char str[256];
│ │ ├── sprintf(str, %05.2f%% %s, confidence, classLabel);
│ │ └── font-OverlayText(image, input-GetWidth(), input-GetHeight(),
│ │ str, 5, 5 n * (font-GetSize() 5),
│ │ make_float4(255,255,255,255), make_float4(0,0,0,100));
│ ├── if (output ! NULL)
│ │ ├── output-Render(image, input-GetWidth(), input-GetHeight());
│ │ ├── char str[256];
│ │ ├── sprintf(str, TensorRT %i.%i.%i | %s | Network %.0f FPS, NV_TENSORRT_MAJOR, NV_TENSORRT_MINOR, NV_TENSORRT_PATCH, net-GetNetworkName(), net-GetNetworkFPS());
│ │ └── output-SetStatus(str);
│ │ └── if (!output-IsStreaming())
│ │ └── break;
│ └── net-PrintProfilerTimes();
├── Destroy resources
│ ├── LogVerbose(imagenet: shutting down...\n);
│ ├── SAFE_DELETE(input);
│ ├── SAFE_DELETE(output);
│ ├── SAFE_DELETE(net);
└── LogVerbose(imagenet: shutdown complete.\n);return 0;4. 参考资料
【1】jetson-inference - Classifying Images with ImageNet
5. 补充
5.1 第一次运行模型本地适应初始化
第一次运行神经网络虽然模型是预训练的但是本地部署还是有个初始化过程好像是建立一些cache的过程具体有待进一步研究。
注有知道为什么是这样也请评论区告诉我谢谢 imagenet can’t work as readme says, see attached log #1858 could not find engine cache … MonoDepth-FCN-Mobilenet/monodepth_fcn_mobilenet.onnx.1.1.8602.GPU.FP16.engine ? #1855 What’s wrong with imagenet/detectnet, continous printf?
5.2 samba软连接
注share请替换为samba共享目录比如home
ubuntu22.04 配置
[global]
allow insecure wide links yes[share]
follow symlinks yes
wide links yes之前的版本
[global]
unix extensions no[share]
follow symlinks yes
wide links yes
