环境
tensorflow = 1.12.0bazel = 0.18.1ubuntu = 16.04python = 3.6.2
安装 bazel (0.18.1)
如果tensorflow是1.12.0
,那么必须安装指定版本0.18.1
的bazel,不然会出现很多的错误无法解决。
wget https://github.com/bazelbuild/bazel/releases/download/0.18.1/bazel-0.18.1-installer-linux-x86_64.sh chmod +x bazel-0.18.1-installer-linux-x86_64.sh ./bazel-0.18.1-installer-linux-x86_64.sh --user
下载tensorflow工程代码
git clone https://github.com/tensorflow/tensorflow.git
编译转换工具
cd tensorflow/ bazel build tensorflow/python/tools:freeze_graphbazel build tensorflow/contrib/lite/toco:toco
生成tflite_graph.pb文件
cd models/research/object_detection
python export_tflite_ssd_graph.py \--pipeline_config_path=data/ssd_mobilenet_v1_coco.config \--trained_checkpoint_prefix=data/training/model.ckpt-28189 \--output_directory=data/output \--add_postprocessing_op=true
利用bazel生成tflite文件
bazel-bin/tensorflow/contrib/lite/toco/toco \--input_file=tflite_graph.pb \--output_file=detect.tflite \--input_shapes=1,300,300,3 \--input_arrays=normalized_input_image_tensor \--output_arrays='TFLite_Detection_PostProcess','TFLite_Detection_PostProcess:1','TFLite_Detection_PostProcess:2','TFLite_Detection_PostProcess:3' \--inference_type=QUANTIZED_UINT8 \--mean_values=128 \--std_values=128 \--change_concat_input_ranges=false \ --default_ranges_min=0 \ --default_ranges_max=6 \ --allow_custom_ops
在Android上测试
在下面的目录中有tensorflow lite的例子,可以替换原来的detect.tflite
文件,修改对应的coco_labels_list.txt
文件,建议改成不一样的名称,修改代码,不然运行的时候,detect.tflite
和coco_labels_list.txt
会重新下载,又被覆盖掉了