Faster-RCNN-TensorFlow-Python3.5在Win10上配置运行

1.在https://github.com/dBeker/Faster-RCNN-TensorFlow-Python3.5地址上下载该项目到本地；

2.利用anaaconda新建python3.5.0的环境，

conda create --name py35 python==3.5.0

 

2.选择python 3.5的环境

activate py35

 

3.利用pip下载画红线的相关包

4.

注：如果出现下图问题，在该地址下下载Visual C++ 2015 build tools https://go.microsoft.com/fwlink/?LinkId=691126

 

5.

Download the training, validation, test data and VOCdevkit

wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar

Extract all of these tars into one directory named VOCdevkit

tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar

It should have this basic structure

$VOCdevkit/                           # development kit
$VOCdevkit/VOCcode/                   # VOC utility code
$VOCdevkit/VOC2007                    # image sets, annotations, etc.
# ... and several other directories ...

 

6.在此链接上下载vgg16预训练模型，http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz，并将其设置为“data \ imagenet_weights \ vgg16.ckpt”。

注：imagenet_weights文件夹是自己新建

7.运行命令

python train.py