Question

我正在尝试在pycharm中创建CNN。当我运行代码时，控制台输出

RuntimeError: You must compile your model before using it.

这是我的代码：

#!/usr/bin/env python
# -*- coding: utf-8 -*-o
from keras.models import Sequential
from keras.layers import Dense, MaxPool2D, Flatten, Conv2D, Dropout
from keras.preprocessing import image
from keras.optimizers import adadelta
generator = image.ImageDataGenerator(  
                rescale=1./255,
                featurewise_center=False, 
                samplewise_center=False, 
                featurewise_std_normalization=False, 
                samplewise_std_normalization=False, 
                zca_whitening=False, 
                rotation_range=10,
                width_shift_range=0.1,
                height_shift_range=0.1,
                horizontal_flip=True,
                vertical_flip=False,
               )
dateset = generator.flow_from_directory(  
               shuffle=True,
               batch_size=100,
               target_size=(80, 80),
               directory='/Users/username/Documents/Project AI/Date set/blood-cells/dataset2-master/images/TRAIN')


def get_model():
        model = Sequential()
        model.add(Conv2D(80, (3, 3), strides=(1, 1), activation='relu'))
        model.add(Conv2D(64, (3, 3), strides=(1, 1), activation='relu', 
                  input_shape=(80, 80, 3)))
        model.add(MaxPool2D(pool_size=(2, 2)))
        model.add(Conv2D(64, (3, 3), strides=(1, 1), activation='relu'))
        model.add(Dropout(0.25))
        model.add(Flatten())
        model.add(Dense(128, activation='relu'))
        model.add(Dropout(0.5))
        model.add(Dense(4, activation='softmax'))
        model.compile(optimizer=adadelta(lr=0.001), 
        loss='categorical_crossentropy', metrics=['accuracy'])
        return model


nn = get_model()
nn.fit_generator(dateset, steps_per_epoch=None, epochs=30, verbose=1)

这是pycharm Python控制台的输出：

Traceback (most recent call last):
  File "<input>", line 1, in <module>
  File "/Applications/PyCharm.app/Contents/helpers/pydev/_pydev_bundle/pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "/Applications/PyCharm.app/Contents/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/Users/username/Documents/Project AI/Src/CNN.py", line 43, in <module>
nn.fit_generator(dateset, steps_per_epoch=None, epochs=30, verbose=1)
  File "/Users/username/Documents/Project AI/venv/lib/python3.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
  File "/Users/username/Documents/Project AI/venv/lib/python3.7/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
  File "/Users/username/Documents/Project AI/venv/lib/python3.7/sitepackages/keras/engine/training_generator.py", line 40, in fit_generator
model._make_train_function()
  File "/Users/yangzichen/Documents/Project AI/venv/lib/python3.7/site-packages/keras/engine/training.py", line 496, in _make_train_function
  raise RuntimeError('You must compile your model before using it.')
RuntimeError: You must compile your model before using it.

Answer 1

类似您面临此已知错误的缝隙： https://github.com/tensorflow/tensorflow/issues/18287

另一种可能的解决方案是在第一层而不是第二层中定义input_shape

关于编译keras模型的问题

1 个答案: