如何部署CNN文件

Question

我已经使用此代码训练了一个模型...

https://github.com/shantanuo/pandas_examples/blob/master/tensorflow/simages_train_waiting.ipynb

我的文件已经准备好了，但是该如何部署呢？

https://s3.ap-south-1.amazonaws.com/studentimages162a/cnn.h5

我尝试使用托管解决方案panini.ai，但它不接受h5文件。我试图将其转换为csv，但这没有用。我也试过用烧瓶

https://github.com/mtobeiyf/keras-flask-deploy-webapp

我在尝试运行Docker容器时遇到此错误...

# docker run -v /tmp/:/tmp/ -p 5000:5000 keras_flask_app
Using TensorFlow backend.
Traceback (most recent call last):
  File "app.py", line 26, in <module>
    model = load_model(MODEL_PATH)
  File "/usr/local/lib/python2.7/site-packages/keras/engine/saving.py", line 419, in load_model
    model = _deserialize_model(f, custom_objects, compile)
  File "/usr/local/lib/python2.7/site-packages/keras/engine/saving.py", line 221, in _deserialize_model
    model_config = f['model_config']
  File "/usr/local/lib/python2.7/site-packages/keras/utils/io_utils.py", line 302, in __getitem__
    raise ValueError('Cannot create group in read only mode.')
ValueError: Cannot create group in read only mode.

换句话说如何使用cnn.h5文件？

---

我正在尝试使用此代码...

from keras.models import Sequential
from keras.layers import Dense, Activation

def build_model():
    model = Sequential()

    model.add(Dense(output_dim=64, input_dim=100))
    model.add(Activation("relu"))
    model.add(Dense(output_dim=10))
    model.add(Activation("softmax"))
    model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
    return model

model2 = build_model()
model2.load_weights('cnn.h5')

并得到错误：

ValueError: You are trying to load a weight file containing 4 layers into a model with 2 layers.

Answer 1

关于第一个错误，我的问题是flask应用尝试加载完整的模型（即使用配置）：

 model = load_model(MODEL_PATH)

而训练后，您仅节省重量：

cnn.save_weights('cnn.h5')

尝试改为使用cnn.save('cnn.h5')。

在第二种情况下，您的模型定义与训练后的模型不匹配。实际上，它是完全不同的模型，完全没有卷积层。相应的模型定义为：

def build_model():
    model = Sequential()

    model.add(Conv2D(filters=32, 
           kernel_size=(2,2), 
           strides=(1,1),
           padding='same',
           input_shape=(IMG_SIZE,IMG_SIZE,NB_CHANNELS),
           data_format='channels_last'))


    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2,2),
                           strides=2))

    model.add(Dropout(0.4))

    model.add(Conv2D(filters=64,
                     kernel_size=(2,2),
                     strides=(1,1),
                     padding='valid'))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2,2),
                           strides=2))

    model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
    return model