最新【图像分类】手撕ResNet——复现ResNet（Keras,Tensorflow 2

import tensorflow as tf

from tensorflow import keras

from tensorflow.keras import layers, Sequential

第一个残差模块

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()

self.downsample.add(layers.Conv2D(filter_num, (1, 1), strides=stride))

else:

self.downsample = lambda x: x

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

out = self.conv1(input)

out = self.bn1(out)

out = self.relu(out)

out = self.conv2(out)

out = self.bn2(out)

identity = self.downsample(input)

output = layers.add([out, identity])

output = tf.nn.relu(output)

return output

class ResNet(keras.Model):

def init(self, layer_dims, num_classes=10):

super(ResNet, self).init()

预处理层

self.padding = keras.layers.ZeroPadding2D((3, 3))

self.stem = Sequential([

layers.Conv2D(64, (7, 7), strides=(2, 2)),

layers.BatchNormalization(),

layers.Activation(‘relu’),

layers.MaxPool2D(pool_size=(3, 3), strides=(2, 2), padding=‘same’)

])

resblock

self.layer1 = self.build_res