• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

Project: iAI (GitHub Link)

• iAI-master
  • src
    • linux_env_set.md
    • ai_model_optimization.md
    • ai_algorithms.md
    • fix_pip
      • ez_setup.py
    • softRoute
      • softroute.md
    • ss
    • wps
    • opencv
    • tmux
      • PowerlineSymbols.otf
      • tmux_conf.md
      • _.tmux.conf
      • _.tmux.conf.local
      • tmux_cheatsheet.md
    • Sponsor
      • alipay.JPG
      • wechat.JPG
    • ai_framework.md
    • linux
      • shell
        • shell.vsdx
      • nanopi-r1
    • fonts
    • ss.md
    • ai_base_env.md
    • linux_library.md
    • ffmpeg.md
    • vscode
      • README.md
    • ai_server_FAQ.md
    • ai
      • pytorch.md
      • tensorflow.md
      • loss-function.md
      • weights.md
      • transfer-learning.md
      • caffe.md
      • caffe_tools
        • create_caffe_lmdb_rgb.sh
        • create_caffe_filelist.sh
        • make_myself_mean.sh
        • create_caffe_lmdb_gray.sh
        • convert_binaryproto_to_npy.py
        • parse_log
          • parse_log.sh
          • plot_training_log.py.example
          • extract_seconds.py
          • plot.py
          • plot_training_log.py
          • parse_log.py
      • receptive_field.md
      • caffe_protofiles
        • resnet-protofiles
          • ResNet_34_train_val.prototxt
          • ResNet_18_train_val.prototxt
          • ResNet_50_train_val.prototxt
          • solver.prototxt
          • ResNet_101_train_val.prototxt
          • ResNet_101_deploy.prototxt
          • generator.py
          • ResNet_152_deploy.prototxt
          • README.md
          • ResNet_50_deploy.prototxt
          • ResNet_152_train_val.prototxt
    • GL-iNet-AR750-官方固件安装SSR-Plus-插件.md
    • algorithm
    • nanopi-r1.md
    • tensorrt
      • tensorrt-5.0.2.6
        • samples-python
          • sampleCharRNN
            • Makefile
            • sampleCharRNN.cpp
          • sampleGoogleNet
            • Makefile
            • sampleGoogleNet.cpp
            • README.md
          • trtexec
            • Makefile
            • giexec
            • trtexec.cpp
          • sampleMovieLensMPS
            • Makefile
            • sampleMovieLensTraining.patch
            • README.txt
            • sampleMovieLensMPS.cpp
          • Makefile
          • sampleNMT
            • Makefile
            • cudaError.h
            • pinnedHostBuffer.h
            • README.txt
            • trtUtil.h
            • sampleNMT.cpp
            • data
              • textWriter.h
              • dataWriter.cpp
              • bleuScoreWriter.h
              • textWriter.cpp
              • limitedSamplesDataReader.cpp
              • textReader.cpp
              • dataWriter.h
              • dataReader.h
              • benchmarkWriter.h
              • limitedSamplesDataReader.h
              • vocabulary.cpp
              • benchmarkWriter.cpp
              • sequenceProperties.h
              • vocabulary.h
              • textReader.h
              • bleuScoreWriter.cpp
            • deviceBuffer.h
            • component.h
            • model
              • multiplicativeAlignment.h
              • context.cpp
              • beamSearchPolicy.h
              • slpProjection.cpp
              • componentWeights.h
              • lstmEncoder.cpp
              • lstmEncoder.h
              • decoder.h
              • context.h
              • likelihood.h
              • encoder.h
              • slpEmbedder.h
              • lstmDecoder.cpp
              • slpProjection.h
              • beamSearchPolicy.cpp
              • embedder.h
              • slpAttention.cpp
              • debugUtil.cpp
              • debugUtil.h
              • softmaxLikelihood.h
              • slpAttention.h
              • lstmDecoder.h
              • softmaxLikelihood.cpp
              • attention.h
              • componentWeights.cpp
              • multiplicativeAlignment.cpp
              • alignment.h
              • likelihoodCombinationOperator.h
              • slpEmbedder.cpp
              • projection.h
            • chptToBin.py
            • trtUtil.cpp
          • sampleUffSSD
            • Makefile
            • config.py
            • sampleUffSSD.cpp
            • README.txt
            • BatchStreamPPM.h
          • sampleMLP
            • Makefile
            • sampleMLP.cpp
            • convert_weights.py
            • README.txt
            • update_mlp.patch
          • sampleMNIST
            • Makefile
            • sampleMNIST.cpp
            • README.md
          • common
            • common.h
            • half.h
            • BatchStream.h
            • sampleConfig.h
            • argsParser.h
            • parserOnnxConfig.h
            • dumpTFWts.py
            • buffers.h
          • sampleUffMNIST
            • Makefile
            • sampleUffMNIST.cpp
          • sampleMNISTAPI
            • sampleMNISTAPI.cpp
            • Makefile
          • sampleFasterRCNN
            • sampleFasterRCNN.cpp
            • Makefile
            • README.txt
            • factoryFasterRCNN.h
          • samplePlugin
            • Makefile
            • fp16.h
            • samplePlugin.cpp
          • python
            • uff_custom_plugin
              • plugin
                • customClipPlugin.cpp
                • clipKernel.h
                • customClipPlugin.h
                • clipKernel.cu
              • lenet5.py
              • CMakeLists.txt
              • __init__.py
              • README.md
              • requirements.txt
              • mnist_uff_custom_plugin.py
            • yolov3_onnx
              • data_processing.py
              • coco_labels.txt
              • yolov3_to_onnx.py
              • onnx_to_tensorrt.py
              • README.md
              • requirements.txt
            • fc_plugin_caffe_mnist
              • plugin
                • FullyConnected.h
                • pyFullyConnected.cpp
              • sample.py
              • CMakeLists.txt
              • __init__.py
              • README.md
              • requirements.txt
            • introductory_parser_samples
              • uff_resnet50.py
              • README.md
              • caffe_resnet50.py
              • requirements.txt
              • onnx_resnet50.py
            • common.py
            • end_to_end_tensorflow_mnist
              • sample.py
              • model.py
              • README.md
              • requirements.txt
            • network_api_pytorch_mnist
              • sample.py
              • model.py
              • README.md
              • requirements.txt
            • uff_ssd
              • utils
                • coco.py
                • engine.py
                • model.py
                • mAP.py
                • boxes.py
                • __init__.py
                • inference.py
                • voc.py
                • paths.py
              • detect_objects.py
              • images
                • image_details.txt
              • plugin
                • FlattenConcat.cpp
              • voc_evaluation.py
              • CMakeLists.txt
              • README.md
              • requirements.txt
          • sampleINT8API
            • Makefile
            • README.md
            • sampleINT8API.cpp
          • sampleSSD
            • Makefile
            • batchPrepare.py
            • PrepareINT8CalibrationBatches.sh
            • README.md
            • sampleSSD.cpp
          • getDigits
            • Makefile
            • download-digits-model.py
            • Makefile.digits
            • README.txt
          • Makefile.config
          • sampleMovieLens
            • preprocess.py
            • Makefile
            • sampleMovieLensTraining.patch
            • sampleMovieLens.cpp
            • README.txt
          • sampleINT8
            • CalibrationTablemnist
            • sampleINT8.cpp
            • Makefile
            • BatchStream.h
            • LegacyCalibrator.h
            • int8_caffe.patch
          • sampleOnnxMNIST
            • Makefile
            • README
            • sampleOnnxMNIST.cpp
      • tensorrt-6.0.1.5
        • samples
          • sampleCharRNN
            • Makefile
            • README.md
            • sampleCharRNN.cpp
          • sampleGoogleNet
            • Makefile
            • sampleGoogleNet.cpp
            • README.md
          • trtexec
            • Makefile
            • giexec
            • README.md
            • trtexec.cpp
          • sampleMovieLensMPS
            • preprocess.py
            • Makefile
            • sampleMovieLensTraining.patch
            • README.md
            • sampleMovieLensMPS.cpp
          • Makefile
          • sampleReformatFreeIO
            • Makefile
            • sampleReformatFreeIO.cpp
            • README.md
          • sampleNMT
            • Makefile
            • cudaError.h
            • pinnedHostBuffer.h
            • trtUtil.h
            • get_newstest2015.sh
            • sampleNMT.cpp
            • data
              • textWriter.h
              • dataWriter.cpp
              • bleuScoreWriter.h
              • textWriter.cpp
              • limitedSamplesDataReader.cpp
              • textReader.cpp
              • dataWriter.h
              • dataReader.h
              • benchmarkWriter.h
              • limitedSamplesDataReader.h
              • vocabulary.cpp
              • benchmarkWriter.cpp
              • sequenceProperties.h
              • vocabulary.h
              • textReader.h
              • bleuScoreWriter.cpp
            • deviceBuffer.h
            • README.md
            • component.h
            • model
              • multiplicativeAlignment.h
              • beamSearchPolicy.h
              • slpProjection.cpp
              • componentWeights.h
              • lstmEncoder.cpp
              • lstmEncoder.h
              • decoder.h
              • likelihood.h
              • encoder.h
              • slpEmbedder.h
              • lstmDecoder.cpp
              • slpProjection.h
              • beamSearchPolicy.cpp
              • embedder.h
              • slpAttention.cpp
              • debugUtil.cpp
              • debugUtil.h
              • contextNMT.h
              • contextNMT.cpp
              • softmaxLikelihood.h
              • slpAttention.h
              • lstmDecoder.h
              • softmaxLikelihood.cpp
              • attention.h
              • componentWeights.cpp
              • multiplicativeAlignment.cpp
              • alignment.h
              • likelihoodCombinationOperator.h
              • slpEmbedder.cpp
              • projection.h
            • chptToBin.py
            • trtUtil.cpp
          • sampleUffSSD
            • Makefile
            • config.py
            • sampleUffSSD.cpp
            • README.md
          • sampleMLP
            • Makefile
            • sampleMLP.cpp
            • convert_weights.py
            • README.md
            • update_mlp.patch
          • sampleMNIST
            • Makefile
            • sampleMNIST.cpp
            • README.md
          • sampleDynamicReshape
            • Makefile
            • sampleDynamicReshape.cpp
            • README.md
          • common
            • sampleUtils.h
            • common.h
            • sampleEngines.cpp
            • half.h
            • sampleEngines.h
            • getOptions.cpp
            • BatchStream.h
            • EntropyCalibrator.h
            • getOptions.h
            • logger.cpp
            • ErrorRecorder.h
            • sampleConfig.h
            • argsParser.h
            • parserOnnxConfig.h
            • sampleOptions.h
            • dumpTFWts.py
            • logging.h
            • sampleOptions.cpp
            • logger.h
            • buffers.h
          • sampleUffMNIST
            • Makefile
            • sampleUffMNIST.cpp
            • README.md
          • sampleMNISTAPI
            • sampleMNISTAPI.cpp
            • Makefile
            • README.md
          • sampleFasterRCNN
            • sampleFasterRCNN.cpp
            • Makefile
            • README.md
            • factoryFasterRCNN.h
          • samplePlugin
            • Makefile
            • fp16.h
            • fcPlugin.h
            • samplePlugin.cpp
            • README.md
          • python
            • engine_refit_mnist
              • sample.py
              • model.py
              • README.md
              • requirements.txt
            • uff_custom_plugin
              • plugin
                • customClipPlugin.cpp
                • clipKernel.h
                • customClipPlugin.h
                • clipKernel.cu
              • lenet5.py
              • sample.py
              • CMakeLists.txt
              • __init__.py
              • README.md
              • requirements.txt
            • yolov3_onnx
              • data_processing.py
              • coco_labels.txt
              • yolov3_to_onnx.py
              • onnx_to_tensorrt.py
              • README.md
              • requirements.txt
            • fc_plugin_caffe_mnist
              • plugin
                • FullyConnected.h
                • pyFullyConnected.cpp
              • sample.py
              • CMakeLists.txt
              • __init__.py
              • README.md
              • requirements.txt
            • int8_caffe_mnist
              • calibrator.py
              • sample.py
              • README.md
              • requirements.txt
            • introductory_parser_samples
              • uff_resnet50.py
              • README.md
              • caffe_resnet50.py
              • requirements.txt
              • onnx_resnet50.py
            • common.py
            • end_to_end_tensorflow_mnist
              • sample.py
              • model.py
              • README.md
              • requirements.txt
            • network_api_pytorch_mnist
              • sample.py
              • model.py
              • README.md
              • requirements.txt
            • uff_ssd
              • utils
                • coco.py
                • engine.py
                • model.py
                • mAP.py
                • boxes.py
                • __init__.py
                • inference.py
                • voc.py
                • paths.py
              • detect_objects.py
              • images
                • image_details.txt
              • plugin
                • FlattenConcat.cpp
              • voc_evaluation.py
              • CMakeLists.txt
              • README.md
              • requirements.txt
          • sampleINT8API
            • Makefile
            • README.md
            • sampleINT8API.cpp
          • sampleSSD
            • Makefile
            • batchPrepare.py
            • PrepareINT8CalibrationBatches.sh
            • README.md
            • requirements.txt
            • sampleSSD.cpp
          • Makefile.config
          • sampleUffPluginV2Ext
            • Makefile
            • README.md
            • sampleUffPluginV2Ext.cpp
          • sampleMovieLens
            • preprocess.py
            • Makefile
            • sampleMovieLensTraining.patch
            • sampleMovieLens.cpp
            • README.md
          • sampleINT8
            • sampleINT8.cpp
            • Makefile
            • int8_caffe.patch
            • README.md
          • sampleOnnxMNIST
            • Makefile
            • sampleOnnxMNIST.cpp
            • README.md
      • tensorrt-4.0.1.6
        • caffe_to_tensorrt.ipynb
        • tf_to_tensorrt.ipynb
        • examples-python
          • custom_layers
            • custom_layers.py
            • tensorrtplugins
              • src
                • FullyConnected.h
              • setup.py
              • tensorrtplugins
                • __init__.py
              • setup.cfg
              • README.md
              • interfaces
                • plugins.i
              • MANIFEST.in
          • pytorch_to_trt
            • mnist.py
            • pytorch_to_trt.py
          • caffe_to_trt
            • caffe_mnist.py
          • googlenet.py
          • uff_mnist.py
          • onnx_mnist.py
          • lite_examples
            • pyt_lite_engine.py
            • caffe_lite_engine.py
            • tf_lite_engine.py
            • plan_lite_engine.py
          • resnet_as_a_service
            • resnet_as_a_service.py
            • query.sh
          • mnist_api.py
          • tf_to_trt
            • tf_to_trt.py
            • lenet5.py
          • sample_onnx
            • sample_onnx.py
        • manually_construct_tensorrt_engine.ipynb
        • samples-cpp
          • sampleCharRNN
            • Makefile
            • sampleCharRNN.cpp
          • sampleGoogleNet
            • Makefile
            • sampleGoogleNet.cpp
          • trtexec
            • Makefile
            • giexec
            • trtexec.cpp
          • Makefile
          • sampleNMT
            • Makefile
            • cudaError.h
            • pinnedHostBuffer.h
            • README.txt
            • trtUtil.h
            • sampleNMT.cpp
            • data
              • textWriter.h
              • dataWriter.cpp
              • bleuScoreWriter.h
              • textWriter.cpp
              • limitedSamplesDataReader.cpp
              • textReader.cpp
              • dataWriter.h
              • dataReader.h
              • benchmarkWriter.h
              • limitedSamplesDataReader.h
              • vocabulary.cpp
              • benchmarkWriter.cpp
              • sequenceProperties.h
              • vocabulary.h
              • textReader.h
              • bleuScoreWriter.cpp
            • deviceBuffer.h
            • component.h
            • model
              • multiplicativeAlignment.h
              • context.cpp
              • beamSearchPolicy.h
              • slpProjection.cpp
              • componentWeights.h
              • lstmEncoder.cpp
              • lstmEncoder.h
              • decoder.h
              • context.h
              • likelihood.h
              • encoder.h
              • slpEmbedder.h
              • lstmDecoder.cpp
              • slpProjection.h
              • beamSearchPolicy.cpp
              • embedder.h
              • slpAttention.cpp
              • debugUtil.cpp
              • debugUtil.h
              • softmaxLikelihood.h
              • slpAttention.h
              • lstmDecoder.h
              • softmaxLikelihood.cpp
              • attention.h
              • componentWeights.cpp
              • multiplicativeAlignment.cpp
              • alignment.h
              • likelihoodCombinationOperator.h
              • slpEmbedder.cpp
              • projection.h
            • chptToBin.py
            • trtUtil.cpp
          • sampleUffSSD
            • Makefile
            • config.py
            • sampleUffSSD.cpp
            • README.txt
            • BatchStreamPPM.h
          • sampleMNIST
            • Makefile
            • sampleMNIST.cpp
          • common
            • common.h
            • sampleConfig.h
            • dumpTFWts.py
          • sampleUffMNIST
            • Makefile
            • sampleUffMNIST.cpp
          • sampleMNISTAPI
            • sampleMNISTAPI.cpp
            • Makefile
          • sampleFasterRCNN
            • sampleFasterRCNN.cpp
            • Makefile
            • README.txt
            • factoryFasterRCNN.h
          • samplePlugin
            • Makefile
            • fp16.h
            • samplePlugin.cpp
          • getDigits
            • Makefile
            • download-digits-model.py
            • Makefile.digits
            • README.txt
          • Makefile.config
          • sampleMovieLens
            • Makefile
            • sampleMovieLensTraining.patch
            • sampleMovieLens.cpp
            • README.txt
          • sampleINT8
            • sampleINT8.cpp
            • Makefile
            • BatchStream.h
            • LegacyCalibrator.h
            • int8_caffe.patch
          • sampleOnnxMNIST
            • Makefile
            • README
            • sampleOnnxMNIST.cpp
      • tensorrt-3.0.4
        • caffe_to_tensorrt.ipynb
        • tf_to_trt.py
        • examples-pyhon
          • custom_layers
            • custom_layers.py
            • tensorrtplugins
              • src
                • FullyConnected.h
              • setup.py
              • tensorrtplugins
                • __init__.pyc
                • __init__.py
              • setup.cfg
              • README.md
              • setup.py~
              • interfaces
                • plugins.i
              • MANIFEST.in
          • caffe_to_trt
            • caffe_mnist.py
          • googlenet.py
          • uff_mnist.py
          • lite_examples
            • caffe_lite_engine.py
            • tf_lite_engine.py
            • plan_lite_engine.py
          • resnet_as_a_service
            • resnet_as_a_service.py
            • query.sh
          • mnist_api.py
          • tf_to_trt
            • tf_to_trt.py
            • lenet5.py
        • tf_to_tensorrt.ipynb
        • manually_construct_tensorrt_engine.ipynb
        • samples-cpp
          • sampleCharRNN
            • common.h
            • Makefile
            • common.cpp
            • sampleCharRNN.cpp
          • sampleGoogleNet
            • common.h
            • Makefile
            • sampleGoogleNet.cpp
            • common.cpp
          • Makefile
          • sampleMNIST
            • common.h
            • Makefile
            • sampleMNIST.cpp
            • common.cpp
          • sampleUffMNIST
            • common.h
            • Makefile
            • sampleUffMNIST.cpp
            • common.cpp
          • sampleMNISTAPI
            • common.h
            • sampleMNISTAPI.cpp
            • Makefile
            • common.cpp
          • sampleFasterRCNN
            • common.h
            • sampleFasterRCNN.cpp
            • Makefile
            • README.txt
            • common.cpp
          • samplePlugin
            • common.h
            • Makefile
            • samplePlugin.cpp
            • common.cpp
          • giexec
            • Makefile
            • giexec.cpp
          • getDigits
            • Makefile
            • download-digits-model.py
            • Makefile.digits
            • README.txt
          • Makefile.config
          • sampleINT8
            • common.h
            • sampleINT8.cpp
            • Makefile
            • BatchStream.h
            • LegacyCalibrator.h
            • int8_caffe.patch
            • common.cpp
      • tools
        • gie_cpp
          • common.h
          • gie.hpp
          • common.cpp
          • gie.cpp
        • trt_cpp_caffe_model
          • common.h
          • main.cpp
          • CMakeLists.txt
          • common.cpp
        • tensorflow_engine
          • call_engine_to_infer_one.py
          • tf_to_trt.py
          • uff_to_engine.py
          • call_engine_to_infer_all.py
          • tf_to_uff.py
        • trt_cpp_tf_uff
          • common.h
          • main.cpp
          • CMakeLists.txt
          • common.cpp
        • caffe_engine
          • call_engine_to_infer_one.py
          • call_engine_to_infer_all_print_predict_on_image_6classes.py
          • call_engine_to_infer_all_analysis_error_6classes.py
          • call_engine_to_infer_all_print_predict_on_image.py
          • call_engine_to_infer_all.py
  • img
    • theme5.jpeg
    • theme6.jpeg
    • TjCRx.gif
    • weights
      • math3.svg
      • ArgsComputeOfDeepNetwork.xlsm
      • math1.svg
      • math2.svg
    • eigen.svg
    • receptive_field
    • theme8.jpeg
    • theme7.jpeg
  • LICENSE
  • README.md
  • .gitignore

AI on Ubuntu Platform

AI实验环境搭建和深度学习算法安装实验

安装环境
其他平台环境类似

硬件环境: ROG MAXIMUS XII HERO(WI-FI) / NVIDIA GTX 2080TI / DDR4 32G 3600 / SSD 2T / HDD 4T
系统环境：Ubuntu-16.04-64bit / Ubuntu-18.04-64bit
安装软件：CUDA9.0-CUDA10.2 / cuDNN / TensorRT / OpenCV / caffe / YOLO-V3 / Protobuf / Matlab / VIM 

---

目录

1. AI基础环境搭建和设置

   1. 安装Ubuntu和Windows双系统
      • 有关Ubuntu分区的相关问题
      • Ubuntu与Windows双系统时间同步解决方法
      • 调整grub引导系统顺序
      • 设置grub引导菜单的分辨率
      • 设置grub Menu显示
   2. 安装NVIDIA驱动
      • 安装NVIDIA驱动所需的依赖包
      • 禁用Ubuntu自带的显卡驱动
      • Ubuntu16TLS安装NVIDIA驱动
      • Ubuntu18TLS安装NVIDIA驱动
      • 配置NVIDIA环境变量
      • 查看NVIDIA显卡驱动版本
      • 解决Linux双系统安装卡在启动Logo
   3. 安装CUDA
      • 安装CUDA步骤
      • 修改配置文件
      • 查看CUDA版本
      • 卸载CUDA的方法
   4. 安装cuDNN
      • 下载安装cuDNN
      • cuDNN常见问题
   5. CUDA多版本问题
   6. Anaconda
      • 安装Anaconda
      • 屏蔽Anaconda
      • 重建Anaconda软连接
      • Anaconda虚拟环境
      • 卸载Anaconda
   7. 安装OpenCV
      • 下载OpenCV
      • 编译OpenCV
      • 安装OpenCV
      • 卸载OpenCV
   8. TensorRT
      • 安装TensorRT
        • TensorRT环境变量设置
        • 安装Python的TensorRT包
        • 安装uff
        • 安装graphsurgeon
        • 验证TensorRT是否安装成功
        • TensorRT安装过程中遇到的问题以及解决方法
      • TensorRT生成Engine
        • Caffe模型用TensorRT生成Engine
        • TensorFlow模型用TensorRT生成Engine
        • 将TensorFlow模型生成UFF文件
        • 将UFF文件转为Engine
        • 调用Engine进行推理
        • TensorRT官方实例 >> 资料在src/tensorrt
        • TensorRT Caffe Engine
        • TensorRT Tensorflow Engine
        • Manually Construct Tensorrt Engine
   9. 安装Pytorch
   10. 安装TensorFlow
   11. 安装Caffe
       • Python2下安装Caffe
       • Python3下安装Caffe
   12. 安装Protobuf
   13. Linux MATLAB安装
       • MATLAB 2018安装
       • MATLAB 2019安装

2. AI Algorithms

   • YOLO V3
   • Faster R-CNN
   • Anaconda FAQ
     • Anaconda环境下TensorFlow和Pytorch共存问题
     • Anaconda环境下Python下导入正常Jupyter Notebook中导入莫名出错
   • 深度学习服务器FAQ
     • docker常用命令
     • 多显卡训练问题
     • 远程访问服务器Jupyter Notebook
       • 方法1 ssh远程使用jupyter notebook
       • 方法2 利用jupyter notebook自带的远程访问功能
   • Transfer Learning
   • Loss Function
     • Loss Function简介
     • Loss Function种类
   • 神经网络参数量(weights)计算
   • 特征尺寸(Feature Map)和感受野(Receptive Field)计算

3. AI Framework

   • AI 常用的结构框架
   • TensorFlow
     • Tensorflow to TensorRT Image Classification
     • TensorFlow FAQ
   • Pytorch
     • 将数据转换为Pytorch格式
   • Caffe
     • Caffe训练模型可视化

4. AI Model Optimization

   • 网络量化
   • 网络剪枝

5. Ubuntu FAQ

   • Awesome Software
   • Linux环境变量初始化与对应文件的生效顺序
   • Ubuntu Library
     • Eigen
   • Docker安装与使用
     • Docker安装
     • Docker使用
   • Linuxbrew安装
     • 安装linuxbrew
     • linuxbrew必装包
     • brew常用命令
     • linuxbrew注意事项
   • 监视GPU和CPU资源利用情况
   • Ubuntu每次开机后提示检测到系统程序出现问题的解决方法
   • Ubuntu循环登陆问题
   • 文件夹打开缓慢
   • 安装Python依赖库
     • Python基础库安装
     • Python项目requirements文件的生成和使用
   • 安装Chrome浏览器
   • pip / pip3常见报错
   • 关于Ubuntu 16.04LTS下安装Spyder3的问题
   • 安装Teamviewer
   • 安装搜狗输入法
   • WPS设置
     • 解决WPS启动提示字体未安装错误
     • WPS切换显示语言
     • WPS不能输入中文
   • 安装赛睿霜冻之蓝V2驱动
   • zsh oh-my-zsh默认shell的最佳替代品
     • 查看系统shell环境
     • 安装zsh
     • 安装vimrc
     • 安装oh-my-zsh
     • 安装zsh-autosuggestions
     • 安装zsh-syntax-highlighting
     • 安装colorls
     • 安装fzf
     • 安装navi
   • vim配置
     • YouCompleteMe实现vim自动补全
     • vim最终配置
   • Tmux配置与使用
     • Tmux配置
     • Tmux使用手册
   • FFmpeg的使用教程
   • 远程连接Ubuntu
   • Sublime Text 3配置问题
   • VSCode配置问题
     • Awesome VScode Plugin
     • VScode Tips
     • Ubuntu VScode配置Cpp编译环境
     • VScode环境配置
   • Ubuntu查看和关闭进程
   • Ubuntu后台执行命令
   • Ubuntu程序开机自启
     • 修改系统启动文件
     • Startup Applications
   • 查看系统状态
   • 彻底卸载软件
   • ESXi下安装iKuai和LEDE双软路由
     • 网络拓扑图
     • ESXi
     • iKuai
     • LEDE
     • 设置iKuai和LEDE开机自动启动
   • NanoPi-R1烧写系统
   • GL-iNet AR750 官方固件安装SSR Plus插件
   • Shadowsocks安装
     • Shadowsocks说明
     • 安装Shadowsocks-qt5
     • 安装electron-ssr
     • 配置Chrome浏览器
   • Ubuntu 美化
     • Unity环境
     • GNOME环境
   • Ubuntu启动后GUI界面卡住不动
   • Ubuntu1804使用过程中常遇到的问题

6. 参考资料

   ---

TODO

• [x] 模型大小(参数量)估计
• [x] 感受野计算
• [ ] 网络优化
• [ ] TensorRT自定义层
• [ ] Pytorch model => OONX
• [ ] TensorFlow model => OONX
• [ ] Caffe 源码解读
• [ ] Darknet 源码解读
• [ ] 语义分割
• [ ] 目标追踪

---

参考资料

1. win10下安装Ubuntu16.04双系统
2. Ubuntu 16.04+CUDA 9.1+cuDNN v7+OpenCV 3.4.0+Caffe+PyCharm 完全安装指南
3. cuDNN官方安装指导
4. ubuntu16.04+caffe+cpu+Anaconda3(python3)
5. caffe编译遇到的问题
6. linux安装MATLAB R2018a步骤
7. 关于Ubuntu16.04LTS下Python版本和安装Spyder3的问题？
8. zsh + oh-my-zsh 默认shell的最佳替代品
9. Terminal Experience
10. 远程访问服务器Jupyter Notebook的方法
11. Jupyer Notebook官方指南
12. 设置 jupyter notebook 可远程访问
13. Docker — 从入门到实践
14. Docker 官方 Ubuntu 安装文档
15. .tmux配置
16. Tmux 快捷键 & 速查表
17. TensorRT官方安装指南
18. Anaconda官方给出的卸载方法
19. Eigen是个什么鬼？
20. AW 17 R5 i9 Ubuntu? Linux?
21. Alienware 17 R4 Ubuntu 16.04 WiFi driver
22. 如何计算感受野(Receptive Field)——原理
23. A guide to receptive field arithmetic for Convolutional Neural Networks
24. 关于感受野 (Receptive field) 你该知道的事
25. 特征图尺寸和感受野计算详解
26. 卷积神经网络中的感受野计算（译）
27. 神经网络参数量的计算: 以UNet为例
28. 从AlexNet理解卷积神经网络的一般结构
29. 经典神经网络参数的计算
30. Ubuntu 18.04 NVIDIA驱动安装总结
31. 解决Linux双系统安装卡在启动Logo
32. Ubuntu 18.04 安装 NVIDIA 显卡驱动