本文主要是介绍深度学习-TensorFlow2：TensorFlow2 创建CNN神经网络模型【ResNet模型】，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
自定义ResNet神经网络-Tensorflow【cifar100分类数据集】
import osos.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' # 放在 import tensorflow as tf 之前才有效import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, optimizers, datasets, Sequential
#==========================================自定义ResNet神经网络：开始==========================================
# 两层的残差学习单元 BasicBlock [(3×3)-->(3×3)]形状，如果是三层的BasicBlock，形状则为：[(1×1)-->(3×3)-->(1×1)]
# stride>1时(比如stride=2)，则通过改层Layer后的FeatureMap的大小减半。strides: An integer or tuple/list of 2 integers
class BasicBlock(layers.Layer):def __init__(self, filter_count, stride=1):super(BasicBlock, self).__init__()# ================================F(x) 部分================================# Layer01self.conv1 = layers.Conv2D(filters=filter_count, kernel_size=[3, 3], strides=stride, padding='same') # 如果padding='same'&stride!=1：输出维度是输入维度的stride分之一。self.bn1 = layers.BatchNormalization()self.relu = layers.Activation('relu')# Layer02self.conv2 = layers.Conv2D(filters=filter_count, kernel_size=[3, 3], strides=1, padding='same') # padding='same'&stride==1：输出维度与输入维度一致。self.bn2 = layers.BatchNormalization()# ================================identity(x)部分================================if stride != 1: # 如果 stride != 1，F(x)部分的输入维度减小stride倍。所以利用一层大小为[1×1×filter_count]的卷积层identity_layer设置strides与F(x)部分的stride一致，将输入值x的维度调整为和F(x)的维度一致，即进行SubSampling。然后再进行加和计算 H(x)=x+F(X)self.identity_layer = layers.Conv2D(filters=filter_count, kernel_size=[1, 1], strides=stride)else: # 如果 stride = 1，则F(x)输出值与输入值x的维度保持不变(必须保证F(x)部分的padding='same'才能维度不变)。所以identity_layer部分直接可以和F(x)部分进行加和计算，不需要经过卷积层对x进行维度调整。也可减少参数的使用。self.identity_layer = lambda x: x # lambda匿名函数：输入为x，return xdef call(self, inputs, training=None):# 前向传播 # [b, h, w, c]# ================================F(x) 部分================================# Layer01F_out = self.conv1(inputs)F_out = self.bn1(F_out)F_out = self.relu(F_out)# Layer02F_out = self.conv2(F_out)F_out = self.bn2(F_out)# ================================identity部分================================# x=identity(x)identity_out = self.identity_layer(inputs)# ================================H(x)=F(x)+x================================basic_block_output = layers.add([F_out, identity_out]) # layers.add(): A tensor as the sum of the inputs. It has the same shape as the inputs.basic_block_output = tf.nn.relu(basic_block_output)return basic_block_output# 由多个BasicBlock组成的ResidualBlock
class ResidualBlock:def __init__(self, filter_count, residualBlock_size, stride=1):self.filter_count = filter_countself.residualBlock_size = residualBlock_sizeself.stride = stridedef __call__(self):basic_block_stride_not_1 = BasicBlock(self.filter_count, stride=self.stride) # stride != 1 时的BasicBlock H(x)=x+F(X)，identity_layer进行SubSamplingbasic_block_stride_1 = BasicBlock(self.filter_count, stride=1) # stride = 1 时的BasicBlock H(x)=x+F(X)，identity_layer层的输出为直接返回输入residualBlock = Sequential()residualBlock.add(basic_block_stride_not_1) # 有一个BasicBlock必须是 stride != 1 时的BasicBlockfor _ in range(1, self.residualBlock_size): # 其余的BasicBlock都是 stride == 1 时的BasicBlockresidualBlock.add(basic_block_stride_1)return residualBlock# 由多个ResidualBlock组成的ResidualNet
# residualBlock_size_list：[2, 2, 2, 2] 表示该ResidualNet含有4个ResidualBlock，每个ResidualBlock包含2个BasicBlock
# residualBlock_size_list：[3, 4, 6, 3] 表示该ResidualNet含有4个ResidualBlock，第1个ResidualBlock包含3个BasicBlock，第2个ResidualBlock包含4个BasicBlock，第3个ResidualBlock包含6个BasicBlock，第4个ResidualBlock包含3个BasicBlock
class ResidualNet(keras.Model):def __init__(self, residualBlock_size_list, class_count=100): # class_count：表示全连接层的输出维度，取决于数据集分类的类别总数量(cifar100为100类)super(ResidualNet, self).__init__()# ================================预处理Block================================self.preprocessBlock = Sequential([layers.Conv2D(filters=50, kernel_size=[3, 3], strides=(1, 1)),layers.BatchNormalization(),layers.Activation('relu'),layers.MaxPool2D(pool_size=(2, 2), strides=(1, 1), padding='same')])# ================================所有ResidualBlock================================residualBlock01_size = residualBlock_size_list[0]residualBlock02_size = residualBlock_size_list[1]residualBlock03_size = residualBlock_size_list[2]residualBlock04_size = residualBlock_size_list[3]self.residualBlock1 = ResidualBlock(50, residualBlock01_size, stride=1)() # 第01个ResidualBlock，包含residualBlock01_size个BasicBlock，residualBlock1设置为64通道self.residualBlock2 = ResidualBlock(150, residualBlock02_size, stride=2)() # 第02个ResidualBlock，包含residualBlock02_size个BasicBlock，residualBlock2设置为128通道self.residualBlock3 = ResidualBlock(300, residualBlock03_size, stride=2)() # 第03个ResidualBlock，包含residualBlock03_size个BasicBlock，residualBlock3设置为256通道self.residualBlock4 = ResidualBlock(500, residualBlock04_size, stride=2)() # 第04个ResidualBlock，包含residualBlock04_size个BasicBlock，residualBlock4设置为512通道# ================================输出层================================# output: [b, h, w, 500] 以上步骤输出的FeatureMap的大小[h,w]不太方便计算self.avgpool_Layer = layers.GlobalAveragePooling2D() # 不管输入的每一个FeatureMap的大小[h,w]是多少，取每一个FeatureMap上的所有元素的平均值作为输出。所以该步骤输出的数据维度为[1,500]# 将上一层的维度为[1,500]的输出传给全连接层进行分类，输出维度为[1,class_count]self.fullcon_Layer = layers.Dense(class_count)def call(self, inputs, training=None):# ================================预处理Block================================x = self.preprocessBlock(inputs) # 输出维度：[b, h, w, 50]# ================================所有ResidualBlock================================x = self.residualBlock1(x) # 输出维度：[b, h, w, 50]x = self.residualBlock2(x) # 输出维度：[b, h, w, 150]x = self.residualBlock3(x) # 输出维度：[b, h, w, 300]x = self.residualBlock4(x) # 输出维度：[b, h, w, 500]# ================================输出层================================x = self.avgpool_Layer(x) # 输出维度：[b, 500]x = self.fullcon_Layer(x) # 输出维度：[b, 100]return xdef resnet18():return ResidualNet([2, 2, 2, 2])def resnet34():return ResidualNet([3, 4, 6, 3])#==========================================自定义ResNet神经网络：结束==========================================# 一、获取数据集
(X_train, Y_train), (X_val, Y_val) = datasets.cifar100.load_data()
print('X_train.shpae = {0}，Y_train.shpae = {1}------------type(X_train) = {2}，type(Y_train) = {3}'.format(X_train.shape, Y_train.shape, type(X_train), type(Y_train)))
Y_train = tf.squeeze(Y_train)
Y_val = tf.squeeze(Y_val)
print('X_train.shpae = {0}，Y_train.shpae = {1}------------type(X_train) = {2}，type(Y_train) = {3}'.format(X_train.shape, Y_train.shape, type(X_train), type(Y_train)))# 二、数据处理
# 预处理函数：将numpy数据转为tensor
def preprocess(x, y):x = tf.cast(x, dtype=tf.float32) / 255.y = tf.cast(y, dtype=tf.int32)return x, y# 2.1 处理训练集
# print('X_train.shpae = {0}，Y_train.shpae = {1}------------type(X_train) = {2}，type(Y_train) = {3}'.format(X_train.shape, Y_train.shape, type(X_train), type(Y_train)))
db_train = tf.data.Dataset.from_tensor_slices((X_train, Y_train)) # 此步骤自动将numpy类型的数据转为tensor
db_train = db_train.map(preprocess) # 调用map()函数批量修改每一个元素数据的数据类型
# 从data数据集中按顺序抽取buffer_size个样本放在buffer中，然后打乱buffer中的样本。buffer中样本个数不足buffer_size，继续从data数据集中安顺序填充至buffer_size，此时会再次打乱。
db_train = db_train.shuffle(buffer_size=1000) # 打散db_train中的样本顺序，防止图片的原始顺序对神经网络性能的干扰。
print('db_train = {0}，type(db_train) = {1}'.format(db_train, type(db_train)))
batch_size_train = 500 # 每个batch里的样本数量设置100-200之间合适。
db_batch_train = db_train.batch(batch_size_train) # 将db_batch_train中每sample_num_of_each_batch_train张图片分为一个batch，读取一个batch相当于一次性并行读取sample_num_of_each_batch_train张图片
print('db_batch_train = {0}，type(db_batch_train) = {1}'.format(db_batch_train, type(db_batch_train)))
# 2.2 处理测试集：测试数据集不需要打乱顺序
db_val = tf.data.Dataset.from_tensor_slices((X_val, Y_val)) # 此步骤自动将numpy类型的数据转为tensor
db_val = db_val.map(preprocess) # 调用map()函数批量修改每一个元素数据的数据类型
batch_size_val = 500 # 每个batch里的样本数量设置100-200之间合适。
db_batch_val = db_val.batch(batch_size_val) # 将db_val中每sample_num_of_each_batch_val张图片分为一个batch，读取一个batch相当于一次性并行读取sample_num_of_each_batch_val张图片# 三、构建ResNet神经网络
# 1、构建ResNet神经网络
resnet18_network = resnet18()
resnet18_network.build(input_shape=[None, 32, 32, 3]) # 原始图片维度为：[32, 32, 3]，None表示样本数量，是不确定的值。
# 2、打印神经网络信息
resnet18_network.summary() # 打印卷积神经网络network的简要信息# 四、梯度下降优化器设置
optimizer = optimizers.Adam(lr=1e-3)# 五、整体数据集进行一次梯度下降来更新模型参数，整体数据集迭代一次，一般用epoch。每个epoch中含有batch_step_no个step，每个step中就是设置的每个batch所含有的样本数量。
def train_epoch(epoch_no):print('++++++++++++++++++++++++++++++++++++++++++++第{0}轮Epoch-->Training 阶段：开始++++++++++++++++++++++++++++++++++++++++++++'.format(epoch_no))for batch_step_no, (X_batch, Y_batch) in enumerate(db_batch_train): # 每次计算一个batch的数据，循环结束则计算完毕整体数据的一次梯度下降；每个batch的序号一般用step表示(batch_step_no)print('epoch_no = {0}, batch_step_no = {1}，X_batch.shpae = {2}，Y_batch.shpae = {3}------------type(X_batch) = {4}，type(Y_batch) = {5}'.format(epoch_no, batch_step_no + 1, X_batch.shape, Y_batch.shape, type(X_batch), type(Y_batch)))Y_batch_one_hot = tf.one_hot(Y_batch, depth=100) # One-Hot编码，共有100类 [] => [b,100]print('\tY_train_one_hot.shpae = {0}'.format(Y_batch_one_hot.shape))# 梯度带tf.GradientTape：连接需要计算梯度的”函数“和”变量“的上下文管理器（context manager）。将“函数”(即Loss的定义式)与“变量”(即神经网络的所有参数)都包裹在tf.GradientTape中进行追踪管理with tf.GradientTape() as tape:# Step1. 前向传播/前向运算-->计算当前参数下模型的预测值out_logits = resnet18_network(X_batch) # [b, 32, 32, 3] => [b, 100]print('\tout_logits.shape = {0}'.format(out_logits.shape))# Step2. 计算预测值与真实值之间的损失Loss：交叉熵损失MSE_Loss = tf.losses.categorical_crossentropy(Y_batch_one_hot, out_logits, from_logits=True) # categorical_crossentropy()第一个参数是真实值，第二个参数是预测值，顺序不能颠倒print('\tMSE_Loss.shape = {0}'.format(MSE_Loss.shape))MSE_Loss = tf.reduce_mean(MSE_Loss)print('\t求均值后：MSE_Loss.shape = {0}'.format(MSE_Loss.shape))print('\t第{0}个epoch-->第{1}个batch step的初始时的：MSE_Loss = {2}'.format(epoch_no, batch_step_no + 1, MSE_Loss))# Step3. 反向传播-->损失值Loss下降一个学习率的梯度之后所对应的更新后的各个Layer的参数：W1, W2, W3, B1, B2, B3...# grads为整个全连接神经网络模型中所有Layer的待优化参数trainable_variables [W1, W2, W3, B1, B2, B3...]分别对目标函数MSE_Loss 在 X_batch 处的梯度值，grads = tape.gradient(MSE_Loss, resnet18_network.trainable_variables) # grads为梯度值。MSE_Loss为目标函数，variables为卷积神经网络、全连接神经网络所有待优化参数，# grads, _ = tf.clip_by_global_norm(grads, 15) # 限幅：解决gradient explosion或者gradients vanishing的问题。# print('\t第{0}个epoch-->第{1}个batch step的初始时的参数：'.format(epoch_no, batch_step_no + 1))if batch_step_no == 0:index_variable = 1for grad in grads:print('\t\tgrad{0}：grad.shape = {1}，grad.ndim = {2}'.format(index_variable, grad.shape, grad.ndim))index_variable = index_variable + 1# 进行一次梯度下降print('\t梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：开始')optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables)) # network的所有参数 trainable_variables [W1, W2, W3, B1, B2, B3...]下降一个梯度 w' = w - lr * grad，zip的作用是让梯度值与所属参数前后一一对应print('\t梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：结束\n')print('++++++++++++++++++++++++++++++++++++++++++++第{0}轮Epoch-->Training 阶段：结束++++++++++++++++++++++++++++++++++++++++++++'.format(epoch_no))# 六、模型评估 test/evluation
def evluation(epoch_no):print('++++++++++++++++++++++++++++++++++++++++++++第{0}轮Epoch-->Evluation 阶段：开始++++++++++++++++++++++++++++++++++++++++++++'.format(epoch_no))total_correct, total_num = 0, 0for batch_step_no, (X_batch, Y_batch) in enumerate(db_batch_val):print('epoch_no = {0}, batch_step_no = {1}，X_batch.shpae = {2}，Y_batch.shpae = {3}'.format(epoch_no, batch_step_no + 1, X_batch.shape, Y_batch.shape))# 根据训练模型计算测试数据的输出值outout_logits = resnet18_network(X_batch) # [b, 32, 32, 3] => [b, 100]print('\tout_logits.shape = {0}'.format(out_logits.shape))# print('\tout_logits_fullcon[:1,:] = {0}'.format(out_logits_fullcon[:1, :]))# 利用softmax()函数将network的输出值转为0~1范围的值，并且使得所有类别预测概率总和为1out_logits_prob = tf.nn.softmax(out_logits, axis=1) # out_logits_prob: [b, 100] ~ [0, 1]# print('\tout_logits_prob[:1,:] = {0}'.format(out_logits_prob[:1, :]))out_logits_prob_max_index = tf.cast(tf.argmax(out_logits_prob, axis=1), dtype=tf.int32) # [b, 100] => [b] 查找最大值所在的索引位置 int64 转为 int32# print('\t预测值：out_logits_prob_max_index = {0},\t真实值：Y_train_one_hot = {1}'.format(out_logits_prob_max_index, Y_batch))is_correct_boolean = tf.equal(out_logits_prob_max_index, Y_batch.numpy())# print('\tis_correct_boolean = {0}'.format(is_correct_boolean))is_correct_int = tf.cast(is_correct_boolean, dtype=tf.float32)# print('\tis_correct_int = {0}'.format(is_correct_int))is_correct_count = tf.reduce_sum(is_correct_int)print('\tis_correct_count = {0}\n'.format(is_correct_count))total_correct += int(is_correct_count)total_num += X_batch.shape[0]print('total_correct = {0}---total_num = {1}'.format(total_correct, total_num))acc = total_correct / total_numprint('第{0}轮Epoch迭代的准确度： acc = {1}'.format(epoch_no, acc))print('++++++++++++++++++++++++++++++++++++++++++++第{0}轮Epoch-->Evluation 阶段：结束++++++++++++++++++++++++++++++++++++++++++++'.format(epoch_no))# 七、整体数据迭代多次梯度下降来更新模型参数
def train():epoch_count = 1 # epoch_count为整体数据集迭代梯度下降次数for epoch_no in range(1, epoch_count + 1):print('\n\n利用整体数据集进行模型的第{0}轮Epoch迭代开始:**********************************************************************************************************************************'.format(epoch_no))train_epoch(epoch_no)evluation(epoch_no)print('利用整体数据集进行模型的第{0}轮Epoch迭代结束:**********************************************************************************************************************************'.format(epoch_no))if __name__ == '__main__':train()
打印结果：
X_train.shpae = (50000, 32, 32, 3)，Y_train.shpae = (50000, 1)------------type(X_train) = <class 'numpy.ndarray'>，type(Y_train) = <class 'numpy.ndarray'>
X_train.shpae = (50000, 32, 32, 3)，Y_train.shpae = (50000,)------------type(X_train) = <class 'numpy.ndarray'>，type(Y_train) = <class 'tensorflow.python.framework.ops.EagerTensor'>
db_train = <ShuffleDataset shapes: ((32, 32, 3), ()), types: (tf.float32, tf.int32)>，type(db_train) = <class 'tensorflow.python.data.ops.dataset_ops.ShuffleDataset'>
db_batch_train = <BatchDataset shapes: ((None, 32, 32, 3), (None,)), types: (tf.float32, tf.int32)>，type(db_batch_train) = <class 'tensorflow.python.data.ops.dataset_ops.BatchDataset'>
Model: "residual_net"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
sequential (Sequential) (None, 30, 30, 50) 1600
_________________________________________________________________
sequential_1 (Sequential) (None, 30, 30, 50) 91000
_________________________________________________________________
sequential_2 (Sequential) (None, 15, 15, 150) 685650
_________________________________________________________________
sequential_3 (Sequential) (None, 8, 8, 300) 2886300
_________________________________________________________________
sequential_4 (Sequential) (None, 4, 4, 500) 8260500
_________________________________________________________________
global_average_pooling2d (Gl multiple 0
_________________________________________________________________
dense (Dense) multiple 50100
=================================================================
Total params: 11,975,150
Trainable params: 11,967,050
Non-trainable params: 8,100
_________________________________________________________________利用整体数据集进行模型的第1轮Epoch迭代开始:**********************************************************************************************************************************
++++++++++++++++++++++++++++++++++++++++++++第1轮Epoch-->Training 阶段：开始++++++++++++++++++++++++++++++++++++++++++++
epoch_no = 1, batch_step_no = 1，X_batch.shpae = (500, 32, 32, 3)，Y_batch.shpae = (500,)------------type(X_batch) = <class 'tensorflow.python.framework.ops.EagerTensor'>，type(Y_batch) = <class 'tensorflow.python.framework.ops.EagerTensor'>Y_train_one_hot.shpae = (500, 100)out_logits.shape = (500, 100)MSE_Loss.shape = (500,)求均值后：MSE_Loss.shape = ()第1个epoch-->第1个batch step的初始时的：MSE_Loss = 4.608854293823242grad1：grad.shape = (3, 3, 3, 50)，grad.ndim = 4grad2：grad.shape = (50,)，grad.ndim = 1grad3：grad.shape = (50,)，grad.ndim = 1grad4：grad.shape = (50,)，grad.ndim = 1grad5：grad.shape = (3, 3, 50, 50)，grad.ndim = 4grad6：grad.shape = (50,)，grad.ndim = 1grad7：grad.shape = (50,)，grad.ndim = 1grad8：grad.shape = (50,)，grad.ndim = 1grad9：grad.shape = (3, 3, 50, 50)，grad.ndim = 4grad10：grad.shape = (50,)，grad.ndim = 1grad11：grad.shape = (50,)，grad.ndim = 1grad12：grad.shape = (50,)，grad.ndim = 1grad13：grad.shape = (3, 3, 50, 50)，grad.ndim = 4grad14：grad.shape = (50,)，grad.ndim = 1grad15：grad.shape = (50,)，grad.ndim = 1grad16：grad.shape = (50,)，grad.ndim = 1grad17：grad.shape = (3, 3, 50, 50)，grad.ndim = 4grad18：grad.shape = (50,)，grad.ndim = 1grad19：grad.shape = (50,)，grad.ndim = 1grad20：grad.shape = (50,)，grad.ndim = 1grad21：grad.shape = (3, 3, 50, 150)，grad.ndim = 4grad22：grad.shape = (150,)，grad.ndim = 1grad23：grad.shape = (150,)，grad.ndim = 1grad24：grad.shape = (150,)，grad.ndim = 1grad25：grad.shape = (3, 3, 150, 150)，grad.ndim = 4grad26：grad.shape = (150,)，grad.ndim = 1grad27：grad.shape = (150,)，grad.ndim = 1grad28：grad.shape = (150,)，grad.ndim = 1grad29：grad.shape = (1, 1, 50, 150)，grad.ndim = 4grad30：grad.shape = (150,)，grad.ndim = 1grad31：grad.shape = (3, 3, 150, 150)，grad.ndim = 4grad32：grad.shape = (150,)，grad.ndim = 1grad33：grad.shape = (150,)，grad.ndim = 1grad34：grad.shape = (150,)，grad.ndim = 1grad35：grad.shape = (3, 3, 150, 150)，grad.ndim = 4grad36：grad.shape = (150,)，grad.ndim = 1grad37：grad.shape = (150,)，grad.ndim = 1grad38：grad.shape = (150,)，grad.ndim = 1grad39：grad.shape = (3, 3, 150, 300)，grad.ndim = 4grad40：grad.shape = (300,)，grad.ndim = 1grad41：grad.shape = (300,)，grad.ndim = 1grad42：grad.shape = (300,)，grad.ndim = 1grad43：grad.shape = (3, 3, 300, 300)，grad.ndim = 4grad44：grad.shape = (300,)，grad.ndim = 1grad45：grad.shape = (300,)，grad.ndim = 1grad46：grad.shape = (300,)，grad.ndim = 1grad47：grad.shape = (1, 1, 150, 300)，grad.ndim = 4grad48：grad.shape = (300,)，grad.ndim = 1grad49：grad.shape = (3, 3, 300, 300)，grad.ndim = 4grad50：grad.shape = (300,)，grad.ndim = 1grad51：grad.shape = (300,)，grad.ndim = 1grad52：grad.shape = (300,)，grad.ndim = 1grad53：grad.shape = (3, 3, 300, 300)，grad.ndim = 4grad54：grad.shape = (300,)，grad.ndim = 1grad55：grad.shape = (300,)，grad.ndim = 1grad56：grad.shape = (300,)，grad.ndim = 1grad57：grad.shape = (3, 3, 300, 500)，grad.ndim = 4grad58：grad.shape = (500,)，grad.ndim = 1grad59：grad.shape = (500,)，grad.ndim = 1grad60：grad.shape = (500,)，grad.ndim = 1grad61：grad.shape = (3, 3, 500, 500)，grad.ndim = 4grad62：grad.shape = (500,)，grad.ndim = 1grad63：grad.shape = (500,)，grad.ndim = 1grad64：grad.shape = (500,)，grad.ndim = 1grad65：grad.shape = (1, 1, 300, 500)，grad.ndim = 4grad66：grad.shape = (500,)，grad.ndim = 1grad67：grad.shape = (3, 3, 500, 500)，grad.ndim = 4grad68：grad.shape = (500,)，grad.ndim = 1grad69：grad.shape = (500,)，grad.ndim = 1grad70：grad.shape = (500,)，grad.ndim = 1grad71：grad.shape = (3, 3, 500, 500)，grad.ndim = 4grad72：grad.shape = (500,)，grad.ndim = 1grad73：grad.shape = (500,)，grad.ndim = 1grad74：grad.shape = (500,)，grad.ndim = 1grad75：grad.shape = (500, 100)，grad.ndim = 2grad76：grad.shape = (100,)，grad.ndim = 1梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：开始梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：结束epoch_no = 1, batch_step_no = 2，X_batch.shpae = (500, 32, 32, 3)，Y_batch.shpae = (500,)------------type(X_batch) = <class 'tensorflow.python.framework.ops.EagerTensor'>，type(Y_batch) = <class 'tensorflow.python.framework.ops.EagerTensor'>Y_train_one_hot.shpae = (500, 100)out_logits.shape = (500, 100)MSE_Loss.shape = (500,)求均值后：MSE_Loss.shape = ()第1个epoch-->第2个batch step的初始时的：MSE_Loss = 5.222436428070068梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：开始梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：结束
...
...
...
...
...
epoch_no = 1, batch_step_no = 100，X_batch.shpae = (500, 32, 32, 3)，Y_batch.shpae = (500,)------------type(X_batch) = <class 'tensorflow.python.framework.ops.EagerTensor'>，type(Y_batch) = <class 'tensorflow.python.framework.ops.EagerTensor'>Y_train_one_hot.shpae = (500, 100)out_logits.shape = (500, 100)MSE_Loss.shape = (500,)求均值后：MSE_Loss.shape = ()第1个epoch-->第100个batch step的初始时的：MSE_Loss = 4.207188129425049梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：开始梯度下降步骤-->optimizer.apply_gradients(zip(grads, resnet18_network.trainable_variables))：结束++++++++++++++++++++++++++++++++++++++++++++第1轮Epoch-->Training 阶段：结束++++++++++++++++++++++++++++++++++++++++++++
++++++++++++++++++++++++++++++++++++++++++++第1轮Epoch-->Evluation 阶段：开始++++++++++++++++++++++++++++++++++++++++++++
epoch_no = 1, batch_step_no = 1，X_batch.shpae = (500, 32, 32, 3)，Y_batch.shpae = (500,)out_logits.shape = (500, 100)is_correct_count = 18.0epoch_no = 1, batch_step_no = 2，X_batch.shpae = (500, 32, 32, 3)，Y_batch.shpae = (500,)out_logits.shape = (500, 100)is_correct_count = 27.0
...
...
...epoch_no = 1, batch_step_no = 20，X_batch.shpae = (500, 32, 32, 3)，Y_batch.shpae = (500,)out_logits.shape = (500, 100)is_correct_count = 26.0total_correct = 454---total_num = 10000
第1轮Epoch迭代的准确度： acc = 0.0454
++++++++++++++++++++++++++++++++++++++++++++第1轮Epoch-->Evluation 阶段：结束++++++++++++++++++++++++++++++++++++++++++++
利用整体数据集进行模型的第1轮Epoch迭代结束:**********************************************************************************************************************************Process finished with exit code 0这篇关于深度学习-TensorFlow2：TensorFlow2 创建CNN神经网络模型【ResNet模型】的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
