# 深度学习2.0-35.ResNet-18实战

1147-柳同学

## 热门标签

, ,

### 1. Basic Block的实现

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers,optimizers,Sequential

# 构建层
class BasicBlock(layers.Layer):
def __init__(self,filter_num,stride=1):
super(BasicBlock, self).__init__()

# convolution layer = conv + bn + relu
self.bn1 = layers.BatchNormalization()
self.relu = layers.Activation('relu')   # rulu层没有参数，可以多次使用

# convolution layer = conv + bn + relu
self.bn2 = layers.BatchNormalization()

# 短接层
if stride != 1:
self.downsample = Sequential()
else:
self.downsample = lambda x:x

# 构建前向传播
def call(self,inputs,training=None):
# inputs:[b,h,w,c]
out = self.conv1(inputs)
out = self.bn1(out)
out = self.relu(out)

out = self.conv2(out)
out = self.bn2(out)

identity = self.downsample(inputs)

output = self.relu(output)
# output = tf.nn.relu(output)

return output


### 2.Res Block的实现

    def build_resblock(self,filter_num,blocks,stride=1):
res_blocks = Sequential()
# 下采样-只有一个具有下采样的能力

for _ in range(1,blocks):

return res_blocks


### 3.ResNet的实现

class ResNet(keras.Model):
# layer_dims,比如:[2,2,2,2] 4个Res Block，每个Res Block包含两个BasicBlock
# num_classes=100  100类
def __init__(self,layer_dims,num_classes=100):

super(ResNet, self).__init__()
# 预处理层
self.stem = Sequential([layers.Conv2D(64,kernel_size=(3,3),strides=(1,1)),
layers.BatchNormalization(),
layers.Activation('relu'),
])

# 按照经验chanel从小到大，feature_size从大到小
self.layer1 = self.build_resblock(64,layer_dims[0])
self.layer2 = self.build_resblock(128,layer_dims[1],stride=2)
self.layer3 = self.build_resblock(256,layer_dims[2],stride=2)
self.layer4 = self.build_resblock(512,layer_dims[3],stride=2)

# output: [b,512,h,w],无法直接确定h，w，故可以设置自适应层
# 原理是对512个通道上面的feature像素值做一个平均，得到一个像素的平均值，将512个像素值送到下一层做均值
self.avgpool = layers.GlobalAveragePooling2D()
# 全连接层-做分类
self.fc = layers.Dense(num_classes)

def call(self,inputs,training=None):

x = self.stem(inputs)

x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)

# [b,c]
x = self.avgpool(x)
# [b,c]=>[b,100]
x = self.fc(x)

return x

def build_resblock(self,filter_num,blocks,stride=1):
res_blocks = Sequential()
# 下采样-只有一个具有下采样的能力

for _ in range(1,blocks):

return res_blocks



### 4.ResNet18的实现

import  tensorflow as tf
from    tensorflow import keras
from    tensorflow.keras import layers, Sequential

class BasicBlock(layers.Layer):

def __init__(self, filter_num, stride=1):
super(BasicBlock, self).__init__()

self.conv1 = layers.Conv2D(filter_num, (3, 3), strides=stride, padding='same')
self.bn1 = layers.BatchNormalization()
self.relu = layers.Activation('relu')

self.conv2 = layers.Conv2D(filter_num, (3, 3), strides=1, padding='same')
self.bn2 = layers.BatchNormalization()

if stride != 1:
self.downsample = Sequential()
else:
self.downsample = lambda x:x

def call(self, inputs, training=None):

# [b, h, w, c]
out = self.conv1(inputs)
out = self.bn1(out)
out = self.relu(out)

out = self.conv2(out)
out = self.bn2(out)

identity = self.downsample(inputs)

output = tf.nn.relu(output)

return output

class ResNet(keras.Model):

def __init__(self, layer_dims, num_classes=100): # [2, 2, 2, 2]
super(ResNet, self).__init__()

self.stem = Sequential([layers.Conv2D(64, (3, 3), strides=(1, 1)),
layers.BatchNormalization(),
layers.Activation('relu'),
])

self.layer1 = self.build_resblock(64,  layer_dims[0])
self.layer2 = self.build_resblock(128, layer_dims[1], stride=2)
self.layer3 = self.build_resblock(256, layer_dims[2], stride=2)
self.layer4 = self.build_resblock(512, layer_dims[3], stride=2)

# output: [b, 512, h, w],
self.avgpool = layers.GlobalAveragePooling2D()
self.fc = layers.Dense(num_classes)

def call(self, inputs, training=None):

x = self.stem(inputs)

x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)

# [b, c]
x = self.avgpool(x)
# [b, 100]
x = self.fc(x)

return x

def build_resblock(self, filter_num, blocks, stride=1):

res_blocks = Sequential()
# may down sample

for _ in range(1, blocks):

return res_blocks

def resnet18():
return ResNet([2, 2, 2, 2])

def resnet34():
return ResNet([3, 4, 6, 3])


### 5.ResNet18的实战

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, optimizers, datasets, Sequential
from resnet import resnet18

tf.random.set_seed(2345)

def preprocess(x, y):
# [-1~1]
x = tf.cast(x, dtype=tf.float32) / 255. - 0.5
y = tf.cast(y, dtype=tf.int32)
return x, y

(x, y), (x_test, y_test) = datasets.cifar100.load_data()
y = tf.squeeze(y, axis=1)
y_test = tf.squeeze(y_test, axis=1)
print(x.shape, y.shape, x_test.shape, y_test.shape)

train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000).map(preprocess).batch(128)

test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(preprocess).batch(128)

sample = next(iter(train_db))
print('sample:', sample[0].shape, sample[1].shape,
tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))

def main():

model = resnet18()
model.build(input_shape=(None, 32, 32, 3))
# 查看模型的参数量
model.summary()

for epoch in range(500):

for step, (x, y) in enumerate(train_db):

# [b, 32, 32, 3] => [b, 100]
logits = model(x)
# [b] => [b, 100]
y_onehot = tf.one_hot(y, depth=100)
# compute loss
loss = tf.losses.categorical_crossentropy(y_onehot, logits, from_logits=True)
loss = tf.reduce_mean(loss)

if step % 50 == 0:
print(epoch, step, 'loss:', float(loss))

total_num = 0
total_correct = 0
for x, y in test_db:
logits = model(x)
prob = tf.nn.softmax(logits, axis=1)
pred = tf.argmax(prob, axis=1)
pred = tf.cast(pred, dtype=tf.int32)

correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
correct = tf.reduce_sum(correct)

total_num += x.shape[0]
total_correct += int(correct)

acc = total_correct / total_num
print(epoch, 'acc:', acc)

if __name__ == '__main__':
main()



(50000, 32, 32, 3) (50000,) (10000, 32, 32, 3) (10000,)
sample: (256, 32, 32, 3) (256,) tf.Tensor(-0.5, shape=(), dtype=float32) tf.Tensor(0.5, shape=(), dtype=float32)
Model: "res_net"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
sequential (Sequential)      multiple                  2048
_________________________________________________________________
sequential_1 (Sequential)    multiple                  148736
_________________________________________________________________
sequential_2 (Sequential)    multiple                  526976
_________________________________________________________________
sequential_4 (Sequential)    multiple                  2102528
_________________________________________________________________
sequential_6 (Sequential)    multiple                  8399360
_________________________________________________________________
global_average_pooling2d (Gl multiple                  0
_________________________________________________________________
dense (Dense)                multiple                  51300
=================================================================
Total params: 11,230,948
Trainable params: 11,223,140
Non-trainable params: 7,808
_________________________________________________________________
0 0 loss: 4.604719638824463
0 50 loss: 4.561609745025635
0 100 loss: 4.337265491485596
0 150 loss: 4.3709611892700195
0 acc: 0.0803
1 0 loss: 4.024875164031982
1 50 loss: 3.8826417922973633
1 100 loss: 3.5792930126190186
1 150 loss: 3.672839641571045
1 acc: 0.1549
2 0 loss: 3.5927116870880127
2 50 loss: 3.357438564300537
2 100 loss: 3.4201531410217285
2 150 loss: 3.187776565551758
2 acc: 0.2268
3 0 loss: 3.1957569122314453
3 50 loss: 3.1121461391448975
3 100 loss: 2.817192316055298
3 150 loss: 2.813638210296631
3 acc: 0.2721
4 0 loss: 3.081834316253662


Vieu3.3主题

Q Q 登 录