如何修改导出keras模型以接受b64字符串到RESTful API/Google

Question

导出模型的完整代码：(我已经训练过它，现在从权重文件加载)

def cnn_layers(inputs):
  conv_base= keras.applications.mobilenetv2.MobileNetV2(input_shape=(224,224,3), input_tensor=inputs, include_top=False, weights='imagenet')
  for layer in conv_base.layers[:-200]:
    layer.trainable = False
  last_layer = conv_base.output
  x = GlobalAveragePooling2D()(last_layer)
  x= keras.layers.GaussianNoise(0.3)(x)
  x = Dense(1024,name='fc-1')(x)
  x = keras.layers.BatchNormalization()(x)
  x = keras.layers.advanced_activations.LeakyReLU(0.3)(x)
  x = Dropout(0.4)(x)
  x = Dense(512,name='fc-2')(x)
  x = keras.layers.BatchNormalization()(x)
  x = keras.layers.advanced_activations.LeakyReLU(0.3)(x)
  x = Dropout(0.3)(x)
  out = Dense(10, activation='softmax',name='output_layer')(x)
  return out

model_input = layers.Input(shape=(224,224,3))

model_output = cnn_layers(model_input)

test_model = keras.models.Model(inputs=model_input, outputs=model_output)

weight_path = os.path.join(tempfile.gettempdir(), 'saved_wt.h5')

test_model.load_weights(weight_path)

export_path='export'
from tensorflow.python.saved_model import builder as saved_model_builder
from tensorflow.python.saved_model import utils
from tensorflow.python.saved_model import tag_constants, signature_constants
from tensorflow.python.saved_model.signature_def_utils_impl import build_signature_def, predict_signature_def
from tensorflow.contrib.session_bundle import exporter

builder = saved_model_builder.SavedModelBuilder(export_path)

signature = predict_signature_def(inputs={'image': test_model.input},
                                  outputs={'prediction': test_model.output})

with K.get_session() as sess:
    builder.add_meta_graph_and_variables(sess=sess,
                                         tags=[tag_constants.SERVING],
                                         signature_def_map={'predict': signature})
    builder.save()

其输出(dir 1有saved_model.pb和models dir)：

python /tensorflow/python/tools/saved_model_cli.py show --dir /1 --all是

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['predict']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['image'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 224, 224, 3)
        name: input_1:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['prediction'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 107)
        name: output_layer/Softmax:0
  Method name is: tensorflow/serving/predict

接受字符串：代码是为(224, 224, 3) numpy数组编写的。因此，我对上述代码所做的修改如下：

• 在作为_bytes传递时，应该将_bytes添加到输入中。所以,

predict_signature_def(inputs={'image':......

变到

predict_signature_def(inputs={'image_bytes':.....

• 早些时候，type(test_model.input)是：(224, 224, 3)和dtype: DT_FLOAT。所以,

signature = predict_signature_def(inputs={'image': test_model.input},.....改为(reference)

temp = tf.placeholder(shape=[None], dtype=tf.string)

signature = predict_signature_def(inputs={'image_bytes': temp},.....

编辑：

使用请求发送的代码是：(如注释中提到的)

encoded_image = None
with open('/1.jpg', "rb") as image_file:
    encoded_image = base64.b64encode(image_file.read())
object_for_api = {"signature_name": "predict",
                  "instances": [
                      {
                           "image_bytes":{"b64":encoded_image}
                           #"b64":encoded_image (or this way since "image" is not needed)
                      }]
                  }

p=requests.post(url='http://localhost:8501/v1/models/mnist:predict', json=json.dumps(object_for_api),headers=headers)
print(p)

我得到了<Response [400]>错误。我认为我发送的方式没有错误。需要在导出模型的代码中更改一些内容，特别是在

temp = tf.placeholder(shape=[None], dtype=tf.string)。

Answer 1

查看您提供的文档，您想要做的是获取图像并将其发送到API中。如果您对图像进行编码，则可以轻松地以文本格式传输图像，base64基本上是标准的。因此，我们要做的是创建一个json对象，在正确的位置将图像作为base64，然后将这个json对象发送到REST。python有一个请求库，这使得将python字典作为JSON发送非常容易。

因此，获取图像，对其进行编码，将其放入字典并使用请求将其发送出去：

import requests
import base64

encoded_image = None
with open("image.png", "rb") as image_file:
    encoded_image = base64.b64encode(image_file.read())

object_for_api = {"signature_name": "predict",
                  "instances": [
                      {
                          "image": {"b64": encoded_image}
                      }]
                  }

requests.post(url='http://localhost:8501/v1/models/mnist:predict', json=object_for_api)

您也可以将numpy数组编码到JSON中，但是API文档似乎并不需要这样做。

Answer 2

两个边注：

1. 我鼓励你使用tf.saved_model.simple_save
2. 你会发现model_to_estimator很方便。
3. 虽然您的模型似乎可以用于请求( saved_model_cli的输出显示输入和输出的外部维度都是None )，但是发送浮点数的JSON数组是相当低效的

最后一点，修改代码以完成图像解码服务器端的操作通常更容易，因此您将通过有线发送一个base64编码的JPG或PNG，而不是一个浮动数组。以下是Keras的一个示例(我计划用更简单的代码更新这个答案)。