models.py 文件源码

def lrcn(self):
        """Build a CNN into RNN.
        Starting version from:
            https://github.com/udacity/self-driving-car/blob/master/
                steering-models/community-models/chauffeur/models.py

        Heavily influenced by VGG-16:
            https://arxiv.org/abs/1409.1556

        Also known as an LRCN:
            https://arxiv.org/pdf/1411.4389.pdf
        """
        model = Sequential()

        model.add(TimeDistributed(Conv2D(32, (7, 7), strides=(2, 2),
            activation='relu', padding='same'), input_shape=self.input_shape))
        model.add(TimeDistributed(Conv2D(32, (3,3),
            kernel_initializer="he_normal", activation='relu')))
        model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))

        model.add(TimeDistributed(Conv2D(64, (3,3),
            padding='same', activation='relu')))
        model.add(TimeDistributed(Conv2D(64, (3,3),
            padding='same', activation='relu')))
        model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))

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

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

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

        model.add(TimeDistributed(Flatten()))

        model.add(Dropout(0.5))
        model.add(LSTM(256, return_sequences=False, dropout=0.5))
        model.add(Dense(self.nb_classes, activation='softmax'))

        return model