batch_normalization (bool): 是否使用批归一化
conv_first (bool): conv-bn-active(True) or bn-active-conv (False)层堆叠次序
Returns:
x (tensor): 输出
“”"
conv = keras.layers.Conv2D(num_filters,
kernel_size=kernel_size,
strides=strides,
padding=‘same’,
kernel_initializer=‘he_normal’,
kernel_regularizer=keras.regularizers.l2(1e-4))
x = inputs
if conv_first:
x = conv(x)
if batch_normalization:
x = keras.layers.BatchNormalization()(x)
if activation is not None:
x = keras.layers.Activation(activation)(x)
else:
if batch_normalization:
x = keras.layers.BatchNormalization()(x)
if activation is not None:
x = keras.layers.Activation(activation)(x)
x = conv(x)
return x
def resnet(input_shape,depth,num_classes=10):
“”"ResNet
Arguments:
input_shape (tensor): 输入尺寸
depth (int): 网络层数
num_classes (int): 预测类别数
Return:
model (Model): 模型
“”"
if (depth - 2) % 6 != 0:
raise ValueError(‘depth should be 6n+2’)
#超参数
num_filters = 16
num_res_blocks = int((depth - 2) / 6)
inputs = keras.layers.Input(shape=input_shape)
x = resnet_layer(inputs=inputs)
for stack in range(3):
for res_block in range(num_res_blocks):
strides = 1
if stack > 0 and res_block == 0:
strides = 2
y = resnet_layer(inputs=x,num_filters=num_filters,
strides=strides)
y = resnet_layer(inputs=y,num_filters=num_filters,
activation=None)
if stack > 0 and res_block == 0:
x = resnet_layer(inputs=x,
num_filters=num_filters,
kernel_size=1,
strides=strides,
activation=None,
batch_normalization=False)
x = keras.layers.add([x,y])
x = keras.layers.Activation(‘relu’)(x)
num_filters *= 2
x = keras.layers.AveragePooling2D(pool_size=8)(x)
x = keras.layers.Flatten()(x)
outputs = keras.layers.Dense(num_classes,activation=‘softmax’,
kernel_initializer=‘he_normal’)(x)
model = keras.Model(inputs=inputs,outputs=outputs)
return model
model = resnet_v1(input_shape=input_shape,depth=depth)
数据加载
#加载数据
(x_train,y_train),(x_test,y_test) = keras.datasets.cifar10.load_data()
#计算类别数
num_labels = len(np.unique(y_train))
#转化为one-hot编码
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
#预处理
input_shape = x_train.shape[1:]
x_train = x_train.astype(‘float32’) / 255.
x_test = x_test.astype(‘float32’) / 255.
模型编译
#超参数
batch_size = 64
epochs = 200
#编译模型
model.compile(loss=‘categorical_crossentropy’,optimizer=‘adam’,metrics=[‘acc’])
model.summary()
模型训练
model.fit(x_train,y_train,
batch_size=batch_size,
epochs=epochs,
validation_data=(x_test,y_test),
shuffle=True)
测试模型
scores = model.evaluate(x_test,y_test,batch_size=batch_size,verbose=0)
print('Test loss: ',scores[0])
print('Test accuracy: ',scores[1])
训练过程
自我介绍一下,小编13年上海交大毕业,曾经在小公司待过,也去过华为、OPPO等大厂,18年进入阿里一直到现在。
深知大多数Python工程师,想要提升技能,往往是自己摸索成长或者是报班学习,但对于培训机构动则几千的学费,着实压力不小。自己不成体系的自学效果低效又漫长,而且极易碰到天花板技术停滞不前!
因此收集整理了一份《2024年Python开发全套学习资料》,初衷也很简单,就是希望能够帮助到想自学提升又不知道该从何学起的朋友,同时减轻大家的负担。
既有适合小白学习的零基础资料,也有适合3年以上经验的小伙伴深入学习提升的进阶课程,基本涵盖了95%以上前端开发知识点,真正体系化!
由于文件比较大,这里只是将部分目录大纲截图出来,每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频,并且后续会持续更新
如果你觉得这些内容对你有帮助,可以扫码获取!!!(备注Python)
)
既有适合小白学习的零基础资料,也有适合3年以上经验的小伙伴深入学习提升的进阶课程,基本涵盖了95%以上前端开发知识点,真正体系化!
由于文件比较大,这里只是将部分目录大纲截图出来,每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频,并且后续会持续更新
如果你觉得这些内容对你有帮助,可以扫码获取!!!(备注Python)
![img](https://i-blog.csdnimg.cn/blog_migrate/8e9cf470e1f2dd749732c123a1f76237.jpeg)