TensorFlow在图像识别中的应用
参考资料:http://www.csdn.net/article/2015-12-16/2826496?_t=t
C++ API的使用方法
用C++运行同样的Inception-v3模型
一、下载定义模型的GraphDef文件(在TensorFlow的根目录下运行):
wget https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip -O tensorflow/examples/label_image/data/inception_dec_2015.zip
learning@learning-virtual-machine:~/tensorflow$ wget https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip -O tensorflow/examples/label_image/data/inception_dec_2015.zip
--2016-05-10 11:13:05-- https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip
Resolving storage.googleapis.com (storage.googleapis.com)... 216.58.199.16, 2404:6800:4005:803::2010
Connecting to storage.googleapis.com (storage.googleapis.com)|216.58.199.16|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 88631107 (85M) [application/zip]
Saving to: ‘tensorflow/examples/label_image/data/inception_dec_2015.zip’
tensorflow/examp 100%[===========>] 84.52M 4.50MB/s in 18s
2016-05-10 11:13:24 (4.70 MB/s) - ‘tensorflow/examples/label_image/data/inception_dec_2015.zip’ saved [88631107/88631107]
unzip tensorflow/examples/label_image/data/inception_dec_2015.zip -d tensorflow/examples/label_image/data/
二、编译加载和运行模型的C++代码。
下载并安装TensorFlow,在shell终端执行命令编译例子:
bazel build tensorflow/examples/label_image/…
三、生成二进制可执行程序,然后运行:
bazel-bin/tensorflow/examples/label_image/label_image
出现问题,待解决
ERROR: /home/learning/tensorflow/tensorflow/cc/BUILD:28:1: Linking of rule '//tensorflow/cc:ops/candidate_sampling_ops_gen_cc' failed: gcc failed: error executing command /usr/bin/gcc -o bazel-out/host/bin/tensorflow/cc/ops/candidate_sampling_ops_gen_cc -pthread -no-canonical-prefixes -B/usr/bin -B/usr/bin -pass-exit-codes '-Wl,--build-id=md5' '-Wl,--hash-style=gnu' ... (remaining 3 argument(s) skipped): com.google.devtools.build.lib.shell.BadExitStatusException: Process exited with status 1.
gcc.real: fatal error: -fuse-linker-plugin, but liblto_plugin.so not found
compilation terminated.
INFO: Elapsed time: 5572.445s, Critical Path: 5407.48s
learning@learning-virtual-machine:~/tensorflow$