这篇文章主要介绍keras提供了三种定义模型方式分别是什么，文中介绍的非常详细，具有一定的参考价值，感兴趣的小伙伴们一定要看完！

前言

一、keras提供了三种定义模型的方式

1. 序列式(Sequential) API

序贯(sequential)API允许你为大多数问题逐层堆叠创建模型。虽然说对很多的应用来说，这样的一个手法很简单也解决了很多深度学习网络结构的构建，但是它也有限制－它不允许你创建模型有共享层或有多个输入或输出的网络。

2. 函数式(Functional) API

Keras函数式(functional)API为构建网络模型提供了更为灵活的方式。

它允许你定义多个输入或输出模型以及共享图层的模型。除此之外，它允许你定义动态(ad-hoc)的非周期性(acyclic)网络图。

模型是通过创建层的实例(layer instances)并将它们直接相互连接成对来定义的，然后定义一个模型(model)来指定那些层是要作为这个模型的输入和输出。

3.子类(Subclassing) API

补充知识：keras pytorch 构建模型对比

使用CIFAR10数据集，用三种框架构建Residual_Network作为例子，比较框架间的异同。

数据集格式

pytorch的数据集格式

import torchimport torch.nn as nnimport torchvision# Download and construct CIFAR-10 dataset.train_dataset = torchvision.datasets.CIFAR10(root='../../data/', train=True, download=True)# Fetch one data pair (read data from disk).image, label = train_dataset[0]print (image.size()) # torch.Size([3, 32, 32])print (label) # 6print (train_dataset.data.shape) # (50000, 32, 32, 3)# type(train_dataset.targets)==listprint (len(train_dataset.targets)) # 50000# Data loader (this provides queues and threads in a very simple way).train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)"""# 演示DataLoader返回的数据结构# When iteration starts, queue and thread start to load data from files.data_iter = iter(train_loader)# Mini-batch images and labels.images, labels = data_iter.next()print(images.shape) # torch.Size([100, 3, 32, 32])print(labels.shape) # torch.Size([100]) 可见经过DataLoader后，labels由list变成了pytorch内置的tensor格式"""# 一般使用的话是下面这种# Actual usage of the data loader is as below.for images, labels in train_loader: # Training code should be written here. pass

keras的数据格式

import kerasfrom keras.datasets import cifar10(train_x, train_y) , (test_x, test_y) = cifar10.load_data()print(train_x.shape) # ndarray 类型： (50000, 32, 32, 3)print(train_y.shape) # (50000, 1)

输入网络的数据格式不同

"""1: pytorch 都是内置torch.xxTensor输入网络，而keras的则是原生ndarray类型2: 对于multi-class的其中一种loss，即cross-entropy loss 而言， pytorch的api为 CorssEntropyLoss, 但y_true不能用one-hoe编码！这与keras，tensorflow 都不同。tensorflow相应的api为softmax_cross_entropy 他们的api都仅限于multi-class classification3*: 其实上面提到的api都属于categorical cross-entropy loss, 又叫 softmax loss，是函数内部先进行了 softmax 激活，再经过cross-entropy loss。 这个loss是cross-entropy loss的变种， cross-entropy loss又叫logistic loss 或 multinomial logistic loss。 实现这种loss的函数不包括激活函数，需要自定义。 pytorch对应的api为BCEloss(仅限于 binary classification), tensorflow 对应的api为 log_loss。 cross-entropy loss的第二个变种是 binary cross-entropy loss 又叫 sigmoid cross- entropy loss。 函数内部先进行了sigmoid激活，再经过cross-entropy loss。 pytorch对应的api为BCEWithLogitsLoss, tensorflow对应的api为sigmoid_cross_entropy"""# pytorchcriterion = nn.CrossEntropyLoss()...for epoch in range(num_epochs): for i, (images, labels) in enumerate(train_loader): images = images.to(device) labels = labels.to(device) # Forward pass outputs = model(images) # 对于multi-class cross-entropy loss # 输入y_true不需要one-hot编码 loss = criterion(outputs, labels)...# keras# 对于multi-class cross-entropy loss# 输入y_true需要one-hot编码train_y = keras.utils.to_categorical(train_y,10)...model.fit_generator(datagen.flow(train_x, train_y, batch_size=128), validation_data=[test_x,test_y], epochs=epochs,steps_per_epoch=steps_per_epoch, verbose=1)...

整体流程

keras 流程

model = myModel()model.compile(optimizer=Adam(0.001),loss="categorical_crossentropy",metrics=["accuracy"])model.fit_generator(datagen.flow(train_x, train_y, batch_size=128), validation_data=[test_x,test_y], epochs=epochs,steps_per_epoch=steps_per_epoch, verbose=1, workers=4)#Evaluate the accuracy of the test datasetaccuracy = model.evaluate(x=test_x,y=test_y,batch_size=128)# 保存整个网络model.save("cifar10model.h6")"""# https://blog.csdn.net/jiandanjinxin/article/details/77152530# 使用# keras.models.load_model("cifar10model.h6")# 只保存architecture# json_string = model.to_json() # open('my_model_architecture.json','w').write(json_string) # 使用# from keras.models import model_from_json#model = model_from_json(open('my_model_architecture.json').read()) # 只保存weights# model.save_weights('my_model_weights.h6') #需要在代码中初始化一个完全相同的模型 # model.load_weights('my_model_weights.h6')#需要加载权重到不同的网络结构（有些层一样）中，例如fine-tune或transfer-learning，可以通过层名字来加载模型 # model.load_weights('my_model_weights.h6', by_name=True)"""

pytorch 流程

model = myModel()# Loss and optimizercriterion = nn.CrossEntropyLoss()for epoch in range(num_epochs): for i, (images, labels) in enumerate(train_loader): images = images.to(device) labels = labels.to(device) # Forward pass outputs = model(images) loss = criterion(outputs, labels) # Backward and optimize# 将上次迭代计算的梯度值清0 optimizer.zero_grad() # 反向传播，计算梯度值 loss.backward() # 更新权值参数 optimizer.step() # model.eval()，让model变成测试模式，对dropout和batch normalization的操作在训练和测试的时候是不一样的# eval（）时，pytorch会自动把BN和DropOut固定住，不会取平均，而是用训练好的值。# 不然的话，一旦test的batch_size过小，很容易就会被BN层导致生成图片颜色失真极大。model.eval()with torch.no_grad(): correct = 0 total = 0 for images, labels in test_loader: images = images.to(device) labels = labels.to(device) outputs = model(images) _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum().item() print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))# Save the model checkpoint# 这是只保存了weightstorch.save(model.state_dict(), 'resnet.ckpt')"""# 使用# myModel.load_state_dict(torch.load('params.ckpt'))# 若想保存整个网络（architecture + weights)# torch.save(resnet, 'model.ckpt')# 使用#model = torch.load('model.ckpt')"""

对比流程

#https://blog.csdn.net/dss_dssssd/article/details/83892824"""1: 准备数据(注意数据格式不同）2: 定义网络结构model3: 定义损失函数4: 定义优化算法 optimizer5: 训练-keras5.1:编译模型（传入loss function和optimizer等）5.2:训练模型（fit or fit_generator，传入数据)5: 训练-pytorch迭代训练：5.1:准备好tensor形式的输入数据和标签(可选)5.2:前向传播计算网络输出output和计算损失函数loss5.3:反向传播更新参数以下三句话一句也不能少：5.3.1:将上次迭代计算的梯度值清0optimizer.zero_grad()5.3.2:反向传播，计算梯度值loss.backward()5.3.3:更新权值参数optimizer.step()6: 在测试集上测试-kerasmodel.evaluate6: 在测试集上测试-pytorch 遍历测试集，自定义metric7: 保存网络（可选） 具体实现参考上面代码"""

构建网络

对比网络

1、对于keras，不需要input_channels，函数内部会自动获得，而pytorch则需要显示声明input_channels

2、对于pytorch Conv2d需要指定padding，而keras的则是same和valid两种选项（valid即padding=0）

3、keras的Flatten操作可以视作pytorch中的view

4、keras的dimension一般顺序是（H, W, C) (tensorflow 为backend的话），而pytorch的顺序则是（ C, H, W)

5、具体的变换可以参照下方，但由于没有学过pytorch，keras也刚入门，不能保证正确，日后学的更深入了之后再来看看。

pytorch 构建Residual-network

import torchimport torch.nn as nnimport torchvisionimport torchvision.transforms as transforms# Device configurationdevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')# Hyper-parametersnum_epochs = 80learning_rate = 0.001# Image preprocessing modulestransform = transforms.Compose([ transforms.Pad(4), transforms.RandomHorizontalFlip(), transforms.RandomCrop(32), transforms.ToTensor()])# CIFAR-10 dataset# train_dataset.data.shape#Out[31]: (50000, 32, 32, 3)# train_dataset.targets list# len(list)=5000train_dataset = torchvision.datasets.CIFAR10(root='./data/', train=True, transform=transform, download=True)test_dataset = torchvision.datasets.CIFAR10(root='../../data/', train=False, transform=transforms.ToTensor())# Data loadertrain_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=100, shuffle=True)test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=100, shuffle=False)# 3x3 convolutiondef conv3x3(in_channels, out_channels, stride=1): return nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)# Residual blockclass ResidualBlock(nn.Module): def __init__(self, in_channels, out_channels, stride=1, downsample=None): super(ResidualBlock, self).__init__() self.conv1 = conv3x3(in_channels, out_channels, stride) self.bn1 = nn.BatchNorm2d(out_channels) self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(out_channels, out_channels) self.bn2 = nn.BatchNorm2d(out_channels) self.downsample = downsample def forward(self, x): residual = x out = self.conv1(x) out = self.bn1(out) out = self.relu(out) out = self.conv2(out) out = self.bn2(out) if self.downsample: residual = self.downsample(x) out += residual out = self.relu(out) return out# ResNetclass ResNet(nn.Module): def __init__(self, block, layers, num_classes=10): super(ResNet, self).__init__() self.in_channels = 16 self.conv = conv3x3(3, 16) self.bn = nn.BatchNorm2d(16) self.relu = nn.ReLU(inplace=True) self.layer1 = self.make_layer(block, 16, layers[0]) self.layer2 = self.make_layer(block, 32, layers[1], 2) self.layer3 = self.make_layer(block, 64, layers[2], 2) self.avg_pool = nn.AvgPool2d(8) self.fc = nn.Linear(64, num_classes) def make_layer(self, block, out_channels, blocks, stride=1): downsample = None if (stride != 1) or (self.in_channels != out_channels): downsample = nn.Sequential( conv3x3(self.in_channels, out_channels, stride=stride), nn.BatchNorm2d(out_channels)) layers = [] layers.append(block(self.in_channels, out_channels, stride, downsample)) self.in_channels = out_channels for i in range(1, blocks): layers.append(block(out_channels, out_channels)) # [*[1,2,3]] # Out[96]: [1, 2, 3] return nn.Sequential(*layers) def forward(self, x): out = self.conv(x) # out.shape:torch.Size([100, 16, 32, 32]) out = self.bn(out) out = self.relu(out) out = self.layer1(out) out = self.layer2(out) out = self.layer3(out) out = self.avg_pool(out) out = out.view(out.size(0), -1) out = self.fc(out) return out model = ResNet(ResidualBlock, [2, 2, 2]).to(device)# pip install torchsummary or# git clone https://github.com/sksq96/pytorch-summaryfrom torchsummary import summary# input_size=(C,H,W)summary(model, input_size=(3, 32, 32))images,labels = iter(train_loader).next()outputs = model(images)# Loss and optimizercriterion = nn.CrossEntropyLoss()optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)# For updating learning ratedef update_lr(optimizer, lr): for param_group in optimizer.param_groups: param_group['lr'] = lr# Train the modeltotal_step = len(train_loader)curr_lr = learning_ratefor epoch in range(num_epochs): for i, (images, labels) in enumerate(train_loader): images = images.to(device) labels = labels.to(device) # Forward pass outputs = model(images) loss = criterion(outputs, labels) # Backward and optimize optimizer.zero_grad() loss.backward() optimizer.step() if (i+1) % 100 == 0: print ("Epoch [{}/{}], Step [{}/{}] Loss: {:.4f}" .format(epoch+1, num_epochs, i+1, total_step, loss.item())) # Decay learning rate if (epoch+1) % 20 == 0: curr_lr /= 3 update_lr(optimizer, curr_lr)# Test the modelmodel.eval()with torch.no_grad(): correct = 0 total = 0 for images, labels in test_loader: images = images.to(device) labels = labels.to(device) outputs = model(images) _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum().item() print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))# Save the model checkpointtorch.save(model.state_dict(), 'resnet.ckpt')

keras 对应的网络构建部分

"""#pytorchdef conv3x3(in_channels, out_channels, stride=1): return nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)"""def conv3x3(x,out_channels, stride=1): #out = spatial_2d_padding(x,padding=((1, 1), (1, 1)), data_format="channels_last") return Conv2D(filters=out_channels, kernel_size=[3,3], strides=(stride,stride),padding="same")(x)"""# pytorch# Residual blockclass ResidualBlock(nn.Module): def __init__(self, in_channels, out_channels, stride=1, downsample=None): super(ResidualBlock, self).__init__() self.conv1 = conv3x3(in_channels, out_channels, stride) self.bn1 = nn.BatchNorm2d(out_channels) self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(out_channels, out_channels) self.bn2 = nn.BatchNorm2d(out_channels) self.downsample = downsample def forward(self, x): residual = x out = self.conv1(x) out = self.bn1(out) out = self.relu(out) out = self.conv2(out) out = self.bn2(out) if self.downsample: residual = self.downsample(x) out += residual out = self.relu(out) return out"""def ResidualBlock(x, out_channels, stride=1, downsample=False): residual = x out = conv3x3(x, out_channels,stride) out = BatchNormalization()(out) out = Activation("relu")(out) out = conv3x3(out, out_channels) out = BatchNormalization()(out) if downsample: residual = conv3x3(residual, out_channels, stride=stride) residual = BatchNormalization()(residual) out = keras.layers.add([residual,out]) out = Activation("relu")(out) return out"""#pytorchdef make_layer(self, block, out_channels, blocks, stride=1): downsample = None if (stride != 1) or (self.in_channels != out_channels): downsample = nn.Sequential( conv3x3(self.in_channels, out_channels, stride=stride), nn.BatchNorm2d(out_channels)) layers = [] layers.append(block(self.in_channels, out_channels, stride, downsample)) self.in_channels = out_channels for i in range(1, blocks): layers.append(block(out_channels, out_channels)) # [*[1,2,3]] # Out[96]: [1, 2, 3] return nn.Sequential(*layers)"""def make_layer(x, out_channels, blocks, stride=1): # tf backend: x.output_shape[-1]==out_channels #print("x.shape[-1] ",x.shape[-1]) downsample = False if (stride != 1) or (out_channels != x.shape[-1]): downsample = True out = ResidualBlock(x, out_channels, stride, downsample) for i in range(1, blocks): out = ResidualBlock(out, out_channels) return outdef KerasResidual(input_shape): images = Input(input_shape) out = conv3x3(images,16) # out.shape=(None, 32, 32, 16) out = BatchNormalization()(out) out = Activation("relu")(out) layer1_out = make_layer(out, 16, layers[0]) layer2_out = make_layer(layer1_out, 32, layers[1], 2) layer3_out = make_layer(layer2_out, 64, layers[2], 2) out = AveragePooling2D(pool_size=(8,8))(layer3_out) out = Flatten()(out) # pytorch 的nn.CrossEntropyLoss()会首先执行softmax计算 # 当换成keras时，没有tf类似的softmax_cross_entropy # 自带的categorical_crossentropy不会执行激活操作，因此得在Dense层加上activation out = Dense(units=10, activation="softmax")(out) model = Model(inputs=images,outputs=out) return modelinput_shape=(32, 32, 3)layers=[2, 2, 2]mymodel = KerasResidual(input_shape)mymodel.summary()

pytorch model summary

---------------------------------------------------------------- Layer (type) Output Shape Param #================================================================ Conv2d-1 [-1, 16, 32, 32] 432 BatchNorm2d-2 [-1, 16, 32, 32] 32 ReLU-3 [-1, 16, 32, 32] 0 Conv2d-4 [-1, 16, 32, 32] 2,304 BatchNorm2d-5 [-1, 16, 32, 32] 32 ReLU-6 [-1, 16, 32, 32] 0 Conv2d-7 [-1, 16, 32, 32] 2,304 BatchNorm2d-8 [-1, 16, 32, 32] 32 ReLU-9 [-1, 16, 32, 32] 0 ResidualBlock-10 [-1, 16, 32, 32] 0 Conv2d-11 [-1, 16, 32, 32] 2,304 BatchNorm2d-12 [-1, 16, 32, 32] 32 ReLU-13 [-1, 16, 32, 32] 0 Conv2d-14 [-1, 16, 32, 32] 2,304 BatchNorm2d-15 [-1, 16, 32, 32] 32 ReLU-16 [-1, 16, 32, 32] 0 ResidualBlock-17 [-1, 16, 32, 32] 0 Conv2d-18 [-1, 32, 16, 16] 4,608 BatchNorm2d-19 [-1, 32, 16, 16] 64 ReLU-20 [-1, 32, 16, 16] 0 Conv2d-21 [-1, 32, 16, 16] 9,216 BatchNorm2d-22 [-1, 32, 16, 16] 64 Conv2d-23 [-1, 32, 16, 16] 4,608 BatchNorm2d-24 [-1, 32, 16, 16] 64 ReLU-25 [-1, 32, 16, 16] 0 ResidualBlock-26 [-1, 32, 16, 16] 0 Conv2d-27 [-1, 32, 16, 16] 9,216 BatchNorm2d-28 [-1, 32, 16, 16] 64 ReLU-29 [-1, 32, 16, 16] 0 Conv2d-30 [-1, 32, 16, 16] 9,216 BatchNorm2d-31 [-1, 32, 16, 16] 64 ReLU-32 [-1, 32, 16, 16] 0 ResidualBlock-33 [-1, 32, 16, 16] 0 Conv2d-34 [-1, 64, 8, 8] 18,432 BatchNorm2d-35 [-1, 64, 8, 8] 128 ReLU-36 [-1, 64, 8, 8] 0 Conv2d-37 [-1, 64, 8, 8] 36,864 BatchNorm2d-38 [-1, 64, 8, 8] 128 Conv2d-39 [-1, 64, 8, 8] 18,432 BatchNorm2d-40 [-1, 64, 8, 8] 128 ReLU-41 [-1, 64, 8, 8] 0 ResidualBlock-42 [-1, 64, 8, 8] 0 Conv2d-43 [-1, 64, 8, 8] 36,864 BatchNorm2d-44 [-1, 64, 8, 8] 128 ReLU-45 [-1, 64, 8, 8] 0 Conv2d-46 [-1, 64, 8, 8] 36,864 BatchNorm2d-47 [-1, 64, 8, 8] 128 ReLU-48 [-1, 64, 8, 8] 0 ResidualBlock-49 [-1, 64, 8, 8] 0 AvgPool2d-50 [-1, 64, 1, 1] 0 Linear-51 [-1, 10] 650================================================================Total params: 195,738Trainable params: 195,738Non-trainable params: 0----------------------------------------------------------------Input size (MB): 0.01Forward/backward pass size (MB): 3.63Params size (MB): 0.75Estimated Total Size (MB): 4.38----------------------------------------------------------------

keras model summary

__________________________________________________________________________________________________Layer (type) Output Shape Param # Connected to ==================================================================================================input_26 (InputLayer) (None, 32, 32, 3) 0 __________________________________________________________________________________________________conv2d_103 (Conv2D) (None, 32, 32, 16) 448 input_26[0][0] __________________________________________________________________________________________________batch_normalization_99 (BatchNo (None, 32, 32, 16) 64 conv2d_103[0][0] __________________________________________________________________________________________________activation_87 (Activation) (None, 32, 32, 16) 0 batch_normalization_99[0][0] __________________________________________________________________________________________________conv2d_104 (Conv2D) (None, 32, 32, 16) 2320 activation_87[0][0] __________________________________________________________________________________________________batch_normalization_100 (BatchN (None, 32, 32, 16) 64 conv2d_104[0][0] __________________________________________________________________________________________________activation_88 (Activation) (None, 32, 32, 16) 0 batch_normalization_100[0][0] __________________________________________________________________________________________________conv2d_105 (Conv2D) (None, 32, 32, 16) 2320 activation_88[0][0] __________________________________________________________________________________________________batch_normalization_101 (BatchN (None, 32, 32, 16) 64 conv2d_105[0][0] __________________________________________________________________________________________________add_34 (Add) (None, 32, 32, 16) 0 activation_87[0][0] batch_normalization_101[0][0] __________________________________________________________________________________________________activation_89 (Activation) (None, 32, 32, 16) 0 add_34[0][0] __________________________________________________________________________________________________conv2d_106 (Conv2D) (None, 32, 32, 16) 2320 activation_89[0][0] __________________________________________________________________________________________________batch_normalization_102 (BatchN (None, 32, 32, 16) 64 conv2d_106[0][0] __________________________________________________________________________________________________activation_90 (Activation) (None, 32, 32, 16) 0 batch_normalization_102[0][0] __________________________________________________________________________________________________conv2d_107 (Conv2D) (None, 32, 32, 16) 2320 activation_90[0][0] __________________________________________________________________________________________________batch_normalization_103 (BatchN (None, 32, 32, 16) 64 conv2d_107[0][0] __________________________________________________________________________________________________add_35 (Add) (None, 32, 32, 16) 0 activation_89[0][0] batch_normalization_103[0][0] __________________________________________________________________________________________________activation_91 (Activation) (None, 32, 32, 16) 0 add_35[0][0] __________________________________________________________________________________________________conv2d_108 (Conv2D) (None, 16, 16, 32) 4640 activation_91[0][0] __________________________________________________________________________________________________batch_normalization_104 (BatchN (None, 16, 16, 32) 128 conv2d_108[0][0] __________________________________________________________________________________________________activation_92 (Activation) (None, 16, 16, 32) 0 batch_normalization_104[0][0] __________________________________________________________________________________________________conv2d_110 (Conv2D) (None, 16, 16, 32) 4640 activation_91[0][0] __________________________________________________________________________________________________conv2d_109 (Conv2D) (None, 16, 16, 32) 9248 activation_92[0][0] __________________________________________________________________________________________________batch_normalization_106 (BatchN (None, 16, 16, 32) 128 conv2d_110[0][0] __________________________________________________________________________________________________batch_normalization_105 (BatchN (None, 16, 16, 32) 128 conv2d_109[0][0] __________________________________________________________________________________________________add_36 (Add) (None, 16, 16, 32) 0 batch_normalization_106[0][0] batch_normalization_105[0][0] __________________________________________________________________________________________________activation_93 (Activation) (None, 16, 16, 32) 0 add_36[0][0] __________________________________________________________________________________________________conv2d_111 (Conv2D) (None, 16, 16, 32) 9248 activation_93[0][0] __________________________________________________________________________________________________batch_normalization_107 (BatchN (None, 16, 16, 32) 128 conv2d_111[0][0] __________________________________________________________________________________________________activation_94 (Activation) (None, 16, 16, 32) 0 batch_normalization_107[0][0] __________________________________________________________________________________________________conv2d_112 (Conv2D) (None, 16, 16, 32) 9248 activation_94[0][0] __________________________________________________________________________________________________batch_normalization_108 (BatchN (None, 16, 16, 32) 128 conv2d_112[0][0] __________________________________________________________________________________________________add_37 (Add) (None, 16, 16, 32) 0 activation_93[0][0] batch_normalization_108[0][0] __________________________________________________________________________________________________activation_95 (Activation) (None, 16, 16, 32) 0 add_37[0][0] __________________________________________________________________________________________________conv2d_113 (Conv2D) (None, 8, 8, 64) 18496 activation_95[0][0] __________________________________________________________________________________________________batch_normalization_109 (BatchN (None, 8, 8, 64) 256 conv2d_113[0][0] __________________________________________________________________________________________________activation_96 (Activation) (None, 8, 8, 64) 0 batch_normalization_109[0][0] __________________________________________________________________________________________________conv2d_115 (Conv2D) (None, 8, 8, 64) 18496 activation_95[0][0] __________________________________________________________________________________________________conv2d_114 (Conv2D) (None, 8, 8, 64) 36928 activation_96[0][0] __________________________________________________________________________________________________batch_normalization_111 (BatchN (None, 8, 8, 64) 256 conv2d_115[0][0] __________________________________________________________________________________________________batch_normalization_110 (BatchN (None, 8, 8, 64) 256 conv2d_114[0][0] __________________________________________________________________________________________________add_38 (Add) (None, 8, 8, 64) 0 batch_normalization_111[0][0] batch_normalization_110[0][0] __________________________________________________________________________________________________activation_97 (Activation) (None, 8, 8, 64) 0 add_38[0][0] __________________________________________________________________________________________________conv2d_116 (Conv2D) (None, 8, 8, 64) 36928 activation_97[0][0] __________________________________________________________________________________________________batch_normalization_112 (BatchN (None, 8, 8, 64) 256 conv2d_116[0][0] __________________________________________________________________________________________________activation_98 (Activation) (None, 8, 8, 64) 0 batch_normalization_112[0][0] __________________________________________________________________________________________________conv2d_117 (Conv2D) (None, 8, 8, 64) 36928 activation_98[0][0] __________________________________________________________________________________________________batch_normalization_113 (BatchN (None, 8, 8, 64) 256 conv2d_117[0][0] __________________________________________________________________________________________________add_39 (Add) (None, 8, 8, 64) 0 activation_97[0][0] batch_normalization_113[0][0] __________________________________________________________________________________________________activation_99 (Activation) (None, 8, 8, 64) 0 add_39[0][0] __________________________________________________________________________________________________average_pooling2d_2 (AveragePoo (None, 1, 1, 64) 0 activation_99[0][0] __________________________________________________________________________________________________flatten_2 (Flatten) (None, 64) 0 average_pooling2d_2[0][0] __________________________________________________________________________________________________dense_2 (Dense) (None, 10) 650 flatten_2[0][0] ==================================================================================================Total params: 197,418Trainable params: 196,298Non-trainable params: 1,120__________________________________________________________________________________________________

以上是keras提供了三种定义模型方式分别是什么的所有内容，感谢各位的阅读！希望分享的内容对大家有帮助，更多相关知识，欢迎关注亿速云行业资讯频道！