为什么 keras 模型可以编译但 fit_generator 命令会抛出“模型未编译运行时错误”？

Question

我已经在带有张量流后端的 keras 中设置了一个带有 K 折交叉验证的自定义 CNN。在开始训练之前会调用 model.compile() 函数，但调用 model.fit_generator() 函数会导致运行时错误：“您必须先编译模型，然后才能使用它。”

我使用 ImageDataGenerator 进行数据增强并使用 fit_generator 函数进行训练。

到目前为止，我发现的唯一相关问题与 tensorflow急切执行功能有关，该功能似乎未在 Keras中启用。

这是代码：

模型定义：

model = Sequential()
model.add(Conv2D(24, (5, 5), 
          strides=(1, 1), 
          padding="valid", 
          data_format="channels_last",
          activation='relu', 
          use_bias=True,
          ))#out=96
model.add(Dropout(.25))
model.add(MaxPooling2D(pool_size=(2, 2)))#out=48
model.add(Conv2D(32, (3, 3), 
          strides=(1, 1), 
          padding="valid", 
          data_format="channels_last",
          activation='relu', 
          use_bias=True,
          ))#out=46
model.add(MaxPooling2D(pool_size=(2, 2)))#out=23
model.add(Conv2D(48, (3, 3), 
          strides=(1, 1), 
          padding="valid", 
          data_format="channels_last",
          activation='relu', 
          use_bias=True,
          ))#out=21
model.add(MaxPooling2D(pool_size=(2, 2)))#padding???
model.add(Flatten())
model.add(Dense(3, activation='softmax'))

...这里将是数据初始化...

设置 ImageGenerator：

datagen_training = ImageDataGenerator(
            rotation_range = 20,
            width_shift_range = 0.3,
            height_shift_range=0.3,
            zoom_range=0.2,
            fill_mode = "constant",
            cval = 0,
            vertical_flip = True,
            validation_split = 0.2
            )
datagen_training.fit(data)

模型设置和训练：

rmsprop = optimizers.RMSprop(lr=0.001)#docu says to only tune the learning rate
kf = KFold(n_splits=FOLDS, shuffle = True, random_state=78945)
model.compile(rmsprop, loss = losses.categorical_crossentropy, metrics=[metrics.categorical_accuracy])
acc_hist = []
while True:
    history = object()
    for train_idx, val_idx in kf.split(data, labels):
        x_train, y_train = data[train_idx], labels[train_idx]
        x_val, y_val = data[val_idx], labels[val_idx]
        data_iterator = datagen_training.flow(x_train, y_train, batch_size=BATCH_SIZE)
        history = model.fit_generator(data_iterator, steps_per_epoch=len(x_train) // BATCH_SIZE, epochs=1)
    acc_hist.append(history.history['categorical_accuracy'][0])
    #stop if accuracy doesn't change within 3 epochs
    if stopping_criterion_met:
        break

Answer 1

该模型未编译，因为未构建它，并且未构建该模型，因为input_shape未在第一层中指定。我不确定数据的输入形状，但是第一层的类似内容将使模型得以编译：

model = Sequential()
model.add(Conv2D(24, (5, 5), 
      strides=(1, 1), 
      padding="valid", 
      data_format="channels_last",
      activation='relu', 
      use_bias=True,
      input_shape=(100,100,1)
      ))#out=96