原创 Install Dlib on Ubuntu
sudo apt-get install build-essential cmake pkg-configsudo apt-get install l
原创 開發環境
必備軟件: VNote(主用+git管理)+cherrytree(備用)+leanote(發博客) pycharm(IDE)+kite(代碼自動補全)+virtualenvwrapper(python虛擬環境管理) wiznot
原创 命令使用手冊
Linux command: nautilus /path/to/that/folder 從終端打開文件夾 sudo nvidia-docker run -it --name tf -p 8888:8888 -p 6006:60
原创 量化訓練
tensorflow量化訓練: post-training quantization: 剪枝,稀疏編碼,對模型存儲體積進行壓縮 quatization-aware training: forward F32==>int8 映射,
原创 variables
a tensorflow variable is the best way to represent shared, persistent state manipulated by your program
原创 image retraining
modern image recognition models have millions of parameters. training them from scratch requires a lot
原创 eager execution
tensorflow's eager execution is an imprerative programming environment that evaluates operations immedi
原创 graphs and sessions
tensorflow uses a dataflow graph to represent your computation in terms of the dependencies between ind
原创 creating custom estimators
as the following figure shows, pre-made Estimators are subclasses of the tf.estimator.Estimator base cl
原创 get started with eager execution
uses tensorflow's eager execution to (1)build a model,(2)train the model on example data, and (3)use th
原创 ubuntu tensorflow_gpu setup
(1) install nvidia driver使用如下命令添加GraphicDrivers PPA: sudo add-apt-repository ppa:graphics-drivers/ppa sudo apt-get upda
原创 feature columns
think of feature columns as the intermediaries between raw data and estimators. feature columns are ver
原创 tensors
a tensor is a generalization of vectors and matrices to potentially higher dimensionswhen writing a ten
原创 object detection with deep learning and opencv
a couple weeks ago we learned how to classify images using deep learning and OpenCV 3.3's deep neural n