Deep Feature Flow for Video Recognition 安装

安装github一步步来，但是安装mxnet从官网安装

1、$git clone https://github.com/msracver/Deep-Feature-Flow.git

2、ubuntu系统下

For Linux user, run sh ./init.sh. The scripts will build cython module automatically and create some folders.

输入$ sh ./init.sh

3、安装mxnet（从官网linux为例）http://mxnet.io/get_started/install.html

3.1、 Install build tools and git.

$sudo apt-get update
 $sudo apt-get install -y build-essential git

3.2、安装openblas

$sudo apt-get install -y libopenblas-dev liblapack-dev

3.3、安装opencv

$sudo apt-get install -y libopencv-dev

3.4、下载源码mxnet

$git clone --recursive https://github.com/dmlc/mxnet

     $cd mxnet

$make -j $(nproc) USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1

4、Install the MXNet Python binding

要记得先把deep feature的cxx文件夹下拷过来

Copy operators in $(DFF_ROOT)/dff_rfcn/operator_cxx or $(DFF_ROOT)/rfcn/operator_cxx to $(YOUR_MXNET_FOLDER)/src/operator/contrib by
$cp -r $(DFF_ROOT)/dff_rfcn/operator_cxx/* $(MXNET_ROOT)/src/operator/contrib/								
然后
步骤二
$ sudo apt-get install -y python-dev python-setuptools python-numpy python-pip
$ cd python
$ pip install --upgrade pip
$ pip install -e .
Step 3  Install Graphviz. (Optional, needed for graph visualization using mxnet.viz package).
    
    

     
     
     
     

      
      
$sudo apt-get install graphviz
$pip install graphviz
      
      
最后通过如下代码验证mxnet安装成功是否
      
      
>>> import mxnet as mx
>>> a = mx.nd.ones((2, 3), mx.gpu())
>>> b = a * 2 + 1
>>> b.asnumpy()
array([[ 3.,  3.,  3.],
       [ 3.,  3.,  3.]], dtype=float32)