NTCU_AI

使用 Github ： https://github.com/SidHard/py-yolo2 git clone https://github.com/SidHard/py-yolo2.git cd py-yolo2 在cMakeList.txt 加上  add_definitions(-O4 -g) cmake . (產生Makefile) sudo make 圖中我是遇到各種地方出現 unknown type name 'CvCapture' 根據檔案名稱 添加  #include "opencv2/videoio/videoio_c.h" 不斷重複make 直到100%為止才代表成功 ------------------------------------------------------------------- 參考資料: http://www.jianshu.com/p/3e77cefeb49b http://blog.csdn.net/y275212517/article/details/64441200 https://github.com/leggedrobotics/darknet_ros/issues/1

cifar 10 、 cifar100 圖片集 ---------------------------------------------------- cifar-10：裡面有10個分類，各5000張，共50000張圖片提供訓練 cifar-100：裡面有20個大分類，每個裡面包含5個小分類，各500張圖片，共50000張圖片 ---------------------------------------------------- 可以透過digits提供的python代碼提取出來 https://github.com/NVIDIA/DIGITS/blob/master/docs/StandardDatasets.md#mnist ---------------------------------------------------- 以下已經透過提取後壓縮，可以直接下載格式為png 32x32 像素 cifar-10： https://goo.gl/1vWqgQ cifar-100： https://goo.gl/hkEFTa

基本上需要依賴前面的CUDA、cuDNN 再來安裝Digits ------------------------------------------------------------------------- https://github.com/NVIDIA/DIGITS/blob/master/docs/BuildDigits.md 因為已經裝過了CUDA就不必再裝了 # For Ubuntu 14.04 ML_REPO_PKG=http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1404/x86_64/nvidia-machine-learning-repo-ubuntu1404_4.0-2_amd64.deb # For Ubuntu 16.04 ML_REPO_PKG=http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64/nvidia-machine-learning-repo-ubuntu1604_1.0.0-1_amd64.deb # Install repo packages wget "$ML_REPO_PKG" -O /tmp/ml-repo.deb && sudo dpkg -i /tmp/ml-repo.deb && rm -f /tmp/ml-repo.deb # Download new list of packages sudo apt-get update #安裝依賴項 sudo apt-get install --no-install-recommends git graphviz python-dev python-flask python-flaskext.wtf python-gevent python-h5py python-numpy python-pil python-pip python-scipy python-tk #安裝 sudo apt-get install digits