如何使用 PyTorch 在预训练模型上添加新层？ （给出了 Keras 示例。）
How can I add new layers on pre-trained model with PyTorch? (Keras example given.)
我正在与 Keras 合作，并尝试分析使用具有有意义权重的一些层和具有随机初始化的一些层构建的模型对准确性的影响。
凯拉斯：
我在加载方法上使用 include_top = False 参数加载 VGG19 预训练模型。
model = keras.applications.VGG19(include_top=False, weights="imagenet", input_shape=(img_width, img_height, 3))
PyTorch:
我加载 VGG19 预训练模型，直到与之前加载 Keras 的模型处于同一层。
model = torch.hub.load('pytorch/vision:v0.6.0', 'vgg19', pretrained=True)
new_base = (list(model.children())[:-2])[0]
加载模型后，下面的图像显示了它们的摘要。 (Pytorch, Keras)
到目前为止没有问题。之后，我想在这些预训练模型上添加 Flatten 层和 Fully connected 层。我用 Keras 做到了，但我不能用 PyTorch。
new_model.summary() 的输出是：
我的问题是，如何在 PyTorch 中添加新图层？
如果您只想替换分类器部分，您可以简单地这样做。即：
model = torch.hub.load('pytorch/vision:v0.6.0', 'vgg19', pretrained=True)
model.classifier = nn.Linear(model.classifier[0].in_features, 4096)
print(model)
会给你：
之前：
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(17): ReLU(inplace=True)
(18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(24): ReLU(inplace=True)
(25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(26): ReLU(inplace=True)
(27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(31): ReLU(inplace=True)
(32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(33): ReLU(inplace=True)
(34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(35): ReLU(inplace=True)
(36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
)
之后：
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(17): ReLU(inplace=True)
(18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(24): ReLU(inplace=True)
(25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(26): ReLU(inplace=True)
(27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(31): ReLU(inplace=True)
(32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(33): ReLU(inplace=True)
(34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(35): ReLU(inplace=True)
(36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Linear(in_features=25088, out_features=4096, bias=True)
)
另请注意，当您想要更改现有架构时，您有两个阶段。你首先得到你想要的模块（这就是你在那里所做的），然后你必须将它包装在 nn.Sequential 中，因为你的列表没有实现 forward() 因此你不能真正提供任何东西。它只是模块的集合。
所以你通常需要做这样的事情（作为例子）：
features = nn.ModuleList(your_model.children())[:-1]
model = nn.Sequential(*features)
# carry on with what other changes you want to perform on your model
请注意，如果您想创建一个新模型并打算像这样使用它：
output = model(imgs)
您需要在第二个序列中包装您的功能和新图层。也就是说，做这样的事情：
features = nn.ModuleList(your_model.children())[:-1]
model_features = nn.Sequential(*features)
some_more_layers = nn.Sequential(Layer1,
Layer2,
... )
model = nn.Sequential(model_features,
some_more_layers)
#
output = model(imgs)
否则你必须做类似的事情：
features_output = model.features(imgs)
output = model.classifier(features_output)
来自 PyTorch 教程 "Finetuning TorchVision Models":
Torchvision offers eight versions of VGG with various lengths and some that have batch normalizations layers. Here we use VGG-11 with batch normalization. The output layer is similar to Alexnet, i.e.
(classifier): Sequential(
...
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
Therefore, we use the same technique to modify the output layer
model.classifier[6] = nn.Linear(4096,num_classes)
我正在与 Keras 合作，并尝试分析使用具有有意义权重的一些层和具有随机初始化的一些层构建的模型对准确性的影响。
凯拉斯：
我在加载方法上使用 include_top = False 参数加载 VGG19 预训练模型。
model = keras.applications.VGG19(include_top=False, weights="imagenet", input_shape=(img_width, img_height, 3))
PyTorch:
我加载 VGG19 预训练模型，直到与之前加载 Keras 的模型处于同一层。
model = torch.hub.load('pytorch/vision:v0.6.0', 'vgg19', pretrained=True)
new_base = (list(model.children())[:-2])[0]
加载模型后，下面的图像显示了它们的摘要。 (Pytorch, Keras)
到目前为止没有问题。之后，我想在这些预训练模型上添加 Flatten 层和 Fully connected 层。我用 Keras 做到了，但我不能用 PyTorch。
new_model.summary() 的输出是：
我的问题是，如何在 PyTorch 中添加新图层？
如果您只想替换分类器部分，您可以简单地这样做。即：
model = torch.hub.load('pytorch/vision:v0.6.0', 'vgg19', pretrained=True)
model.classifier = nn.Linear(model.classifier[0].in_features, 4096)
print(model)
会给你：
之前：
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(17): ReLU(inplace=True)
(18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(24): ReLU(inplace=True)
(25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(26): ReLU(inplace=True)
(27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(31): ReLU(inplace=True)
(32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(33): ReLU(inplace=True)
(34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(35): ReLU(inplace=True)
(36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
)
之后：
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(17): ReLU(inplace=True)
(18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(24): ReLU(inplace=True)
(25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(26): ReLU(inplace=True)
(27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(31): ReLU(inplace=True)
(32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(33): ReLU(inplace=True)
(34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(35): ReLU(inplace=True)
(36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Linear(in_features=25088, out_features=4096, bias=True)
)
另请注意，当您想要更改现有架构时，您有两个阶段。你首先得到你想要的模块（这就是你在那里所做的），然后你必须将它包装在 nn.Sequential 中，因为你的列表没有实现 forward() 因此你不能真正提供任何东西。它只是模块的集合。
所以你通常需要做这样的事情（作为例子）：
features = nn.ModuleList(your_model.children())[:-1]
model = nn.Sequential(*features)
# carry on with what other changes you want to perform on your model
请注意，如果您想创建一个新模型并打算像这样使用它：
output = model(imgs)
您需要在第二个序列中包装您的功能和新图层。也就是说，做这样的事情：
features = nn.ModuleList(your_model.children())[:-1]
model_features = nn.Sequential(*features)
some_more_layers = nn.Sequential(Layer1,
Layer2,
... )
model = nn.Sequential(model_features,
some_more_layers)
#
output = model(imgs)
否则你必须做类似的事情：
features_output = model.features(imgs)
output = model.classifier(features_output)
来自 PyTorch 教程 "Finetuning TorchVision Models":
Torchvision offers eight versions of VGG with various lengths and some that have batch normalizations layers. Here we use VGG-11 with batch normalization. The output layer is similar to Alexnet, i.e.
(classifier): Sequential( ... (6): Linear(in_features=4096, out_features=1000, bias=True) )Therefore, we use the same technique to modify the output layer
model.classifier[6] = nn.Linear(4096,num_classes)