ValueError：检查输入时出错：预期density_1_input具有形状（1，224，224），但数组形状为（224，224，1）

Question

我正在使用model.fit_generator ，它给我一个错误，即输入大小与预期大小不匹配。 但是我使用target_size=(224, 224) image_datagen.flow_from_directory使用image_datagen.flow_from_directory重塑了它，我无法将其设置为(1, 224, 224) image_datagen.flow_from_directory target_size=(224, 224) ，否则给了我另一个错误。

我不确定使用train_generator = image_datagen.flow_from_directory(target_size =(224,224))时如何检查输入大小

train_generator = image_datagen.flow_from_directory(
'C:/output/train/',
    class_mode="categorical",
    seed=seed,
    batch_size=batch_size,
    target_size=(input_size, input_size),
    color_mode='grayscale',
    shuffle=True)

valid_generator = image_datagen.flow_from_directory(
    'C:/output/valid/',
    class_mode="categorical",
    seed=seed,
    batch_size=batch_size,
    target_size=(input_size, input_size),
    color_mode='grayscale',
    shuffle=True)


# https://github.com/keras-team/keras/blob/master/keras/callbacks.py
class MyCheckPoint(keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        loss = logs["loss"]
        val_loss = logs["val_loss"]
        fileName = "model.%02d_%0.5f_%0.5f.h5" % (epoch, loss, val_loss)
        self.model.save(fileName)

#weight_saver = MyCheckPoint()

model = models.getVGGModel(num_classes)
#model = models. getStandardModel(input_size)
model.compile(optimizer=Adam(lr=1e-5, decay=1e-8), loss=keras.losses.categorical_crossentropy)
#model.load_weights("weights.26-1.48.h5")

weight_saver = ModelCheckpoint('weights.{epoch:02d}-{val_loss:.2f}.h5',save_best_only=True, save_weights_only=True)
hist = model.fit_generator(train_generator, validation_data=valid_generator, validation_steps=80, steps_per_epoch=400, epochs=200, callbacks=[weight_saver])

def getVGGModel(num_classes):
    model = Sequential()
    model.add(Dense(32, input_shape=(1, 224, 224)))
    # Reshape((784,), input_shape=(1, 224, 224))
    model.add(Conv2D(64, (3, 3), activation='relu', strides=(1,1), padding='same',input_shape=(1, 224, 224), data_format="channels_first"))
    model.add(Conv2D(64, (3, 3), activation='relu', strides=(1,1), padding='same',data_format = 'channels_first'))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2),data_format = 'channels_first'))

    model.add(Conv2D(128, (3, 3), activation='relu', padding='same',data_format = 'channels_first'))
    model.add(Conv2D(128, (3, 3), activation='relu', padding='same', data_format = 'channels_first'))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2), padding='same',data_format = 'channels_first'))

    model.add(Conv2D(256, (3, 3), activation='relu', padding='same',data_format = 'channels_first'))
    model.add(Conv2D(256, (3, 3), activation='relu', padding='same',data_format = 'channels_first'))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2), padding='same',data_format = 'channels_first'))

    model.add(Conv2D(512, (3, 3), activation='relu', padding='same',data_format = 'channels_first'))
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same',data_format = 'channels_first'))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2), padding='same',data_format = 'channels_first'))

    model.add(Conv2D(512, (3, 3), activation='relu', padding='same',data_format = 'channels_first'))
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same',data_format = 'channels_first'))
    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2), padding='same',data_format = 'channels_first'))

    model.add(Flatten())
    model.add(Dense(4096, activation="relu"))
    model.add(Dropout(0.5))
    model.add(Dense(4096, activation="relu"))
    model.add(Dropout(0.5))
    model.add(Dense(num_classes, activation="softmax"))

    return model

Answer 1

问题来自模型的输入：

model.add(Dense(32, input_shape=(1, 224, 224)))

默认情况下target_size=(224, 224)将为您提供一个形状为（ target_size=(224, 224)的张量，其通道位于最后。
但是，您要为模型指定通道优先的输入。

只需将输入更改为：

model.add(Dense(32, input_shape=(224, 224, 1)))

而且当然，您不再需要为所有图层指定data_format，Keras默认使用channel_last。