感谢：https://www.jianshu.com/p/66a0a6fd3cae

 

深度学习和机器学习移动端化是未来趋势，这两年各个大厂都在这方面发力，竞相推出自己移动端的推理框架。

google: Tensorflow Lite

apple: CoreML

facebook: Caffe2

tencent: ncnn

baidu: paddle mobile

xiaomi: MACE

各个平台之间性能有差异。

 

以下介绍框架的转换流程：

一、tensorflow 转 tensorflow lite

移动端深度学习开源框架-前言0

 tensorflow提供官方转换工具toco， 可以直接将tensorflow.pb模型转换为.tflite模型。

使用例子：

toco --graph_def_file=DeeplabV3++_portrait_384_1_05alpha.pb --output_file=DeeplabV3++_portrait_384_1_05alpha.tflite --output_format=TFLITE --input_shape=1,384,384,3 --input_array=input_1 --output_array=output_0 --inference_type=float --allow_custom_ops

 

下面介绍如何查看tensorflow模型中节点名称

1、如何查看checkpoints中节点名称

saver = tf.train.import_meta_graph(/path/to/meta/graph)

sess = tf.Session()

saver.restore(sess, /path/to/checkpoints)

graph = sess.graph

print([node.name for node in graph.as_graph_def().node])

2、 如何查看静态图.pb节点信息：

以simplenet静态图文件为例

"""FIND GRAPH INFO"""
tf_model_path = "./simplenet_V2_8M.pb"
with open(tf_model_path , 'rb') as f:
    serialized = f.read()
tf.reset_default_graph()
original_gdef = tf.GraphDef()
original_gdef.ParseFromString(serialized)

with tf.Graph().as_default() as g:
    tf.import_graph_def(original_gdef, name ='')
    ops = g.get_operations()
    N = len(ops)
    for i in [0,1,2,N-3,N-2,N-1]: # for循环设置输出的节点信息
        print('\n\nop id {} : op type: "{}"'.format(str(i), ops[i].type))
        print('input(s):')
        for x in ops[i].inputs:
            print("name = {}, shape: {}, ".format(x.name, x.get_shape()))
        print('\noutput(s):'),
        for x in ops[i].outputs:
            print("name = {}, shape: {},".format(x.name, x.get_shape()))

 

输出信息如下：

op id 0 : op type: "Placeholder"
input(s):

output(s):
name = input_1:0, shape: (?, 32, 32, 3),


op id 1 : op type: "Const"
input(s):

output(s):
name = block1_conv/kernel:0, shape: (3, 3, 3, 128),


op id 2 : op type: "Identity"
input(s):
name = block1_conv/kernel:0, shape: (3, 3, 3, 128), 

output(s):
name = block1_conv/kernel/read:0, shape: (3, 3, 3, 128),


op id 190 : op type: "MatMul"
input(s):
name = global_average_pooling2d_1/Mean:0, shape: (?, 600), 
name = dense_1/kernel/read:0, shape: (600, 10), 

output(s):
name = dense_1/MatMul:0, shape: (?, 10),


op id 191 : op type: "BiasAdd"
input(s):
name = dense_1/MatMul:0, shape: (?, 10), 
name = dense_1/bias/read:0, shape: (10,), 

output(s):
name = dense_1/BiasAdd:0, shape: (?, 10),


op id 192 : op type: "Softmax"
input(s):
name = dense_1/BiasAdd:0, shape: (?, 10), 

output(s):
name = activation_1/Softmax:0, shape: (?, 10),

提供合适的信息给toco进行转换：

toco --graph_def_file=simplenet_V2_8M.pb --output_file=simplenet_v2_8M.tflite --output_format=TFLITE --input_shape=1,32,32,3 --input_arrays=input_1 --output_arrays=activation_1/Softmax
转换成功之后就会生成.tflite文件，可以用于移动端部署。
 
实际上在直接用于移动端部署之前，需要测试tflite模型的准确度，这就需要直接在Python里面调用tflite
import numpy as np
import tensorflow as tf

# Load TFLite model and allocate tensors.
interpreter = tf.contrib.lite.Interpreter(model_path="converted_model.tflite")
interpreter.allocate_tensors()

# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

# Test model on random input data.
input_shape = input_details[0]['shape']
# change the following line to feed into your own data.
input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
interpreter.set_tensor(input_details[0]['index'], input_data)

interpreter.invoke()
output_data = interpreter.get_tensor(output_details[0]['index'])
print(output_data)
 
二、Tensroflow 转CoreML
CoreML并不提供将tensorflow模型直接转换为mlmodel的工具，提供两种思路：
1、使用keras接口， coreml支持keras转换；
2、使用第三方转换工具tf-coreml
 
以下展开tf-coreml的使用方法
　　首先，将之前保存的checkpoints保存为静态图，.pb格式
　　然后，要输入的参数有：
　　tf_model_path: .pb静态图模型路径
　　mlmodel_path: 生成的CoreML模型路径地址
　　input_name_shape_dict: 网络的输入名称和数据的大小（要根据原始的模型输入确定）　　
　　output_feature_names:网络输出的名称（要根据原始的模型输出确定）
此外，可以对输入的数据做一些归一化处理：
　　image_scale
　　red_bias
　　green_bias
　　blue_bias
 
程序如下所示：
import tensorflow as tf
import tfcoreml
from coremltools.proto import FeatureTypes_pb2 as _FeatureTypes_pb2
import coremltools

""" FIND GRAPH INFO """
tf_model_path = "/tmp//retrained_graph.pb"
with open(tf_model_path , 'rb') as f:
    serialized = f.read()
tf.reset_default_graph()
original_gdef = tf.GraphDef()
original_gdef.ParseFromString(serialized)

with tf.Graph().as_default() as g:
    tf.import_graph_def(original_gdef, name ='')
    ops = g.get_operations()
    N = len(ops)
    for i in [0,1,2,N-3,N-2,N-1]:
        print('\n\nop id {} : op type: "{}"'.format(str(i), ops[i].type))
        print('input(s):')
        for x in ops[i].inputs:
            print("name = {}, shape: {}, ".format(x.name, x.get_shape()))
        print('\noutput(s):'),
        for x in ops[i].outputs:
            print("name = {}, shape: {},".format(x.name, x.get_shape()))

""" CONVERT TF TO CORE ML """
# Model Shape
input_tensor_shapes = {"input:0":[1,224,224,3]} 
# Input Name
image_input_name = ['input:0']
# Output CoreML model path
coreml_model_file = '/tmp/myModel.mlmodel'
# Output name
output_tensor_names = ['final_result:0']
# Label file for classification
class_labels = '/tmp/retrained_labels.txt'

#Convert Process
coreml_model = tfcoreml.convert(
        tf_model_path=tf_model_path,
        mlmodel_path=coreml_model_file,
        input_name_shape_dict=input_tensor_shapes,
        output_feature_names=output_tensor_names,
        image_input_names = image_input_name,
        class_labels = class_labels)

# Get image pre-processing parameters of a saved CoreML model
spec = coremltools.models.utils.load_spec(coreml_model_file)
if spec.WhichOneof('Type') == 'neuralNetworkClassifier':
  nn = spec.neuralNetworkClassifier
  print("neuralNetworkClassifier")
if spec.WhichOneof('Type') == 'neuralNetwork':
  nn = spec.neuralNetwork  
  print("neuralNetwork")
if spec.WhichOneof('Type') == 'neuralNetworkRegressor':
  nn = spec.neuralNetworkRegressor
  print("neuralNetworkClassifierRegressor")

preprocessing = nn.preprocessing[0].scaler
print('channel scale: ', preprocessing.channelScale)
print('blue bias: ', preprocessing.blueBias)
print('green bias: ', preprocessing.greenBias)
print('red bias: ', preprocessing.redBias)

inp = spec.description.input[0]
if inp.type.WhichOneof('Type') == 'imageType':
  colorspace = _FeatureTypes_pb2.ImageFeatureType.ColorSpace.Name(inp.type.imageType.colorSpace)
  print('colorspace: ', colorspace)

coreml_model = tfcoreml.convert(
        tf_model_path=tf_model_path,
        mlmodel_path=coreml_model_file,
        input_name_shape_dict=input_tensor_shapes,
        output_feature_names=output_tensor_names,
        image_input_names = image_input_name,
        class_labels = class_labels,
        red_bias = -1,
        green_bias = -1,
        blue_bias = -1,
        image_scale = 2.0/255.0)
 
coremltools是apple官方转换工具，支持很多平台：
移动端深度学习开源框架-前言0
以下是Keras模型转换coreml模型脚本：
 import coremltools
  import keras
  from keras.models import load_model
  from keras.utils.generic_utils import CustomObjectScope
  class_labels = []
  for i in range(62):
       class_labels.append(str(i))

   with CustomObjectScope({'relu6': keras.applications.mobilenet.relu6}):
      keras_model = load_model('traffic_sign_with_class_weights.h5')
      coreml_model = coremltools.converters.keras.convert(keras_model,
                                                      input_names=['input_1'],
                                                      image_input_names='input_1',
                                                      output_names='activation_1',
                                                      image_scale=2/255.0,
                                                      red_bias=-1,
                                                      green_bias=-1,
                                                      blue_bias=-1,
                                                      class_labels=class_labels)
  
 coreml_model.save('traffic_sign_with_class_weights.mlmodel')