深度学习（五十七）tensorflow andorid yolo物体检测测试

一、修改tensorflow/workspace文件，取消android相关注释：

# Uncomment and update the paths in these entries to build the Android demo.
android_sdk_repository(
    name = "androidsdk",
    api_level = 24,
    # Ensure that you have the build_tools_version below installed in the 
    # SDK manager as it updates periodically.
    build_tools_version = "25.0.2",
    # Replace with path to Android SDK on your system
    path = "/home/research/Android/Sdk",
)
#
# Android NDK r12b is recommended (higher may cause issues with Bazel)
android_ndk_repository(
    name="androidndk",
    path="/home/research/Android/Sdk/ndk-bundle",
    # This needs to be 14 or higher to compile TensorFlow. 
    # Note that the NDK version is not the API level.
    api_level=14)

二、修改 android:build.gradle 中bazel路径，默认的是如下的：

def bazelLocation = '/usr/local/bin/bazel'

但是在该路径下并没有bazel，因此会报如下错：

Error:Execution failed for task ':buildNativeBazel'.
A problem occurred starting process 'command '/usr/local/bin/bazel''

此时只需要把路径改成你的bazel路径就好，比如我的是：

def bazelLocation = '/usr/bin/bazel'

三、代码结构：

基类Classifier.java,三个子类：