TensorFlow Lite toco模型转换官方文档

1.toco
2.python api
3.command line
4.Optimizing tflite for mobile

Multiple output arrays

1.9

curl https://storage.googleapis.com/download.tensorflow.org/models/inception_v1_2016_08_28_frozen.pb.tar.gz \
  | tar xzv -C /tmp
tflite_convert \
  --graph_def_file=/tmp/inception_v1_2016_08_28_frozen.pb \
  --output_file=/tmp/foo.tflite \
  --input_arrays=input \
  --output_arrays=InceptionV1/InceptionV1/Mixed_3b/Branch_1/Conv2d_0a_1x1/Relu,InceptionV1/InceptionV1/Mixed_3b/Branch_2/Conv2d_0a_1x1/Relu

1.8及以下

curl https://storage.googleapis.com/download.tensorflow.org/models/inception_v1_2016_08_28_frozen.pb.tar.gz \
  | tar xzv -C /tmp
bazel run --config=opt \
  tensorflow/contrib/lite/toco:toco -- \
  --input_file=/tmp/inception_v1_2016_08_28_frozen.pb \
  --output_file=/tmp/foo.tflite \
  --input_format=TENSORFLOW_GRAPHDEF \
  --output_format=TFLITE \
  --inference_type=FLOAT \
  --input_shape=1,224,224,3 \
  --input_array=input \
  --output_arrays=InceptionV1/InceptionV1/Mixed_3b/Branch_1/Conv2d_0a_1x1/Relu,InceptionV1/InceptionV1/Mixed_3b/Branch_2/Conv2d_0a_1x1/Relu