VGG_16.py 文件源码

def classifier(base_layers, input_rois, batch_size, nb_classes = 3, trainable=False):

    # compile times tend to be very high, so we use smaller ROI pooling regions to workaround
    if K.backend() == 'tensorflow':
        pooling_regions = 14
        input_shape = (batch_size,14,14,1024)
    elif K.backend() == 'theano':
        pooling_regions = 7
        input_shape = (batch_size,1024,7,7)

    out_roi_pool = RoiPoolingConv(pooling_regions, batch_size)([base_layers, input_rois])
    out = TimeDistributed(Flatten())(out_roi_pool)
    out = TimeDistributed(Dense(4096,activation='relu'))(out)
    out = TimeDistributed(Dropout(0.5))(out)
    out = TimeDistributed(Dense(4096,activation='relu'))(out)
    out = TimeDistributed(Dropout(0.5))(out)

    out_class = TimeDistributed(Dense(nb_classes, activation='softmax', kernel_initializer='zero'), name='dense_class_{}'.format(nb_classes))(out)
    # note: no regression target for bg class
    out_regr = TimeDistributed(Dense(4 * nb_classes, activation='linear', kernel_initializer='zero'), name='dense_regress_{}'.format(nb_classes))(out)
    return [out_class, out_regr]