YOLO V1网络框架( 学习笔记来自:头歌实践教学平台)
网络参数展示图:
输出网络结构:
网络结构: _________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 224, 224, 64) 1792 _________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 112, 112, 64) 0 _________________________________________________________________
conv2d_2 (Conv2D) (None, 112, 112, 192) 110784 _________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 56, 56, 192) 0 _________________________________________________________________
conv2d_3 (Conv2D) (None, 56, 56, 128) 24704 _________________________________________________________________
conv2d_4 (Conv2D) (None, 56, 56, 256) 295168 _________________________________________________________________
conv2d_5 (Conv2D) (None, 56, 56, 256) 65792 _________________________________________________________________
conv2d_6 (Conv2D) (None, 56, 56, 512) 1180160 _________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 28, 28, 512) 0 _________________________________________________________________
conv2d_7 (Conv2D) (None, 28, 28, 256) 131328 _________________________________________________________________
conv2d_8 (Conv2D) (None, 28, 28, 512) 1180160 _________________________________________________________________
conv2d_9 (Conv2D) (None, 28, 28, 256) 131328 _________________________________________________________________
conv2d_10 (Conv2D) (None, 28, 28, 512) 1180160 _________________________________________________________________
conv2d_11 (Conv2D) (None, 28, 28, 256) 131328 _________________________________________________________________
conv2d_12 (Conv2D) (None, 28, 28, 512) 1180160 _________________________________________________________________
conv2d_13 (Conv2D) (None, 28, 28, 256) 131328 _________________________________________________________________
conv2d_14 (Conv2D) (None, 28, 28, 512) 1180160 _________________________________________________________________
conv2d_15 (Conv2D) (None, 28, 28, 512) 262656 _________________________________________________________________
conv2d_16 (Conv2D) (None, 28, 28, 1024) 525312 _________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 14, 14, 1024) 0 _________________________________________________________________
conv2d_17 (Conv2D) (None, 14, 14, 512) 524800 _________________________________________________________________
conv2d_18 (Conv2D) (None, 14, 14, 1024) 4719616 _________________________________________________________________
conv2d_19 (Conv2D) (None, 14, 14, 512) 524800 _________________________________________________________________
conv2d_20 (Conv2D) (None, 14, 14, 1024) 4719616 _________________________________________________________________
conv2d_21 (Conv2D) (None, 14, 14, 1024) 9438208 _________________________________________________________________
conv2d_22 (Conv2D) (None, 7, 7, 1024) 9438208 _________________________________________________________________
conv2d_23 (Conv2D) (None, 7, 7, 1024) 9438208 _________________________________________________________________
conv2d_24 (Conv2D) (None, 7, 7, 1024) 9438208 _________________________________________________________________
flatten_1 (Flatten) (None, 50176) 0 _________________________________________________________________
dense_1 (Dense) (None, 4096) 205524992 _________________________________________________________________
dropout_1 (Dropout) (None, 4096) 0 _________________________________________________________________
dense_2 (Dense) (None, 1470) 6022590 =================================================================
Total params: 267,501,566
Trainable params: 267,501,566
Non-trainable params: 0
_________________________________________________________________
参考代码:
import tensorflow as tf
def createYOLO_v1_Model(tiny=True):
if tiny:
# 序贯模型(Sequential):单输入单输出,一条路通到底,层与层之间只有相邻关系,没有跨层连接。
models = tf.keras.Sequential([
# 卷积层相关参数:卷积核64个,卷积核大小为3*3,步长为2,填充为same,输入图片尺寸为448x448x3,而激活函数为LeakyReLU,超参数为0.1
tf.keras.layers.Conv2D(64, (3, 3), strides=2, padding='same', input_shape=(448, 448, 3), activation=tf.keras.layers.LeakyReLU(0.1)),
# 池化层相关参数:池化大小为2*2,步长为2
tf.keras.layers.MaxPooling2D((2, 2), strides=2),
tf.keras.layers.Conv2D(192, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.MaxPooling2D((2, 2), strides=2),
tf.keras.layers.Conv2D(128, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(256, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(256, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(512, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
# 请在此添加代码,根据左侧展示图补充池化层代码
########## Begin ##########
tf.keras.layers.MaxPooling2D((2, 2), strides=2),
######### End ##########
tf.keras.layers.Conv2D(256, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(512, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(256, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(512, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(256, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(512, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(256, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(512, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(512, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(1024, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.MaxPooling2D((2, 2), strides=2),
tf.keras.layers.Conv2D(512, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(1024, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(512, (1, 1), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(1024, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(1024, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
# 请在此添加代码,根据左侧展示图补充卷积层代码
########## Begin ##########
tf.keras.layers.Conv2D(1024, (3, 3), strides=2, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(1024, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
tf.keras.layers.Conv2D(1024, (3, 3), strides=1, padding='same', activation=tf.keras.layers.LeakyReLU(0.1)),
########## End ##########
# 请在此添加代码,根据左侧内容提示补充扁平层代码
########## Begin ##########
tf.keras.layers.Flatten(),
########## End ##########
# 全连接层
tf.keras.layers.Dense(4096, activation=tf.keras.layers.LeakyReLU(0.1)),
# 请在此添加代码,根据左侧内容提示补充Dropout层代码,超参数是0.5,可以缓解过拟合操作
########## Begin ##########
tf.keras.layers.Dropout(0.6),
########## End ##########
# 输出一个7*7*30的张量
tf.keras.layers.Dense(7*7*30)])
return models
model = createYOLO_v1_Model()
print('网络结构:')
model.summary()