译（四十七）-Pytorch获取模型概要
如有翻译问题欢迎评论指出，谢谢。
Pytorch获取模型概要
Wasi Ahmad asked:
Pytorch 怎么像 Keras 的
model.summary()获得一个模型概要？Model Summary: ____________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ==================================================================================================== input_1 (InputLayer) (None, 1, 15, 27) 0 ____________________________________________________________________________________________________ convolution2d_1 (Convolution2D) (None, 8, 15, 27) 872 input_1[0][0] ____________________________________________________________________________________________________ maxpooling2d_1 (MaxPooling2D) (None, 8, 7, 27) 0 convolution2d_1[0][0] ____________________________________________________________________________________________________ flatten_1 (Flatten) (None, 1512) 0 maxpooling2d_1[0][0] ____________________________________________________________________________________________________ dense_1 (Dense) (None, 1) 1513 flatten_1[0][0] ==================================================================================================== Total params: 2,385 Trainable params: 2,385 Non-trainable params: 0
Answers:
Shubham Chandel - vote: 213
用 pytorch-summary 包可以实现 Keras 的效果。
VGG16 的例子：
from torchvision import models from torchsummary import summary # vgg = models.vgg16() summary(vgg, (3, 224, 224)) # ---------------------------------------------------------------- Layer (type) Output Shape Param # ================================================================ Conv2d-1 [-1, 64, 224, 224] 1,792 ReLU-2 [-1, 64, 224, 224] 0 Conv2d-3 [-1, 64, 224, 224] 36,928 ReLU-4 [-1, 64, 224, 224] 0 MaxPool2d-5 [-1, 64, 112, 112] 0 Conv2d-6 [-1, 128, 112, 112] 73,856 ReLU-7 [-1, 128, 112, 112] 0 Conv2d-8 [-1, 128, 112, 112] 147,584 ReLU-9 [-1, 128, 112, 112] 0 MaxPool2d-10 [-1, 128, 56, 56] 0 Conv2d-11 [-1, 256, 56, 56] 295,168 ReLU-12 [-1, 256, 56, 56] 0 Conv2d-13 [-1, 256, 56, 56] 590,080 ReLU-14 [-1, 256, 56, 56] 0 Conv2d-15 [-1, 256, 56, 56] 590,080 ReLU-16 [-1, 256, 56, 56] 0 MaxPool2d-17 [-1, 256, 28, 28] 0 Conv2d-18 [-1, 512, 28, 28] 1,180,160 ReLU-19 [-1, 512, 28, 28] 0 Conv2d-20 [-1, 512, 28, 28] 2,359,808 ReLU-21 [-1, 512, 28, 28] 0 Conv2d-22 [-1, 512, 28, 28] 2,359,808 ReLU-23 [-1, 512, 28, 28] 0 MaxPool2d-24 [-1, 512, 14, 14] 0 Conv2d-25 [-1, 512, 14, 14] 2,359,808 ReLU-26 [-1, 512, 14, 14] 0 Conv2d-27 [-1, 512, 14, 14] 2,359,808 ReLU-28 [-1, 512, 14, 14] 0 Conv2d-29 [-1, 512, 14, 14] 2,359,808 ReLU-30 [-1, 512, 14, 14] 0 MaxPool2d-31 [-1, 512, 7, 7] 0 Linear-32 [-1, 4096] 102,764,544 ReLU-33 [-1, 4096] 0 Dropout-34 [-1, 4096] 0 Linear-35 [-1, 4096] 16,781,312 ReLU-36 [-1, 4096] 0 Dropout-37 [-1, 4096] 0 Linear-38 [-1, 1000] 4,097,000 ================================================================ Total params: 138,357,544 Trainable params: 138,357,544 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 0.57 Forward/backward pass size (MB): 218.59 Params size (MB): 527.79 Estimated Total Size (MB): 746.96 ----------------------------------------------------------------SpiderWasp42 - vote: 185
虽然不能像 Keras 的
model.summary()一样得到模型详细信息，但通过打印模型你也能得到不同层的信息。例：
from torchvision import models model = models.vgg16() print(model)输出如下：
VGG ( (features): Sequential ( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU (inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): ReLU (inplace) (4): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (6): ReLU (inplace) (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (8): ReLU (inplace) (9): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (11): ReLU (inplace) (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (13): ReLU (inplace) (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (15): ReLU (inplace) (16): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (18): ReLU (inplace) (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (20): ReLU (inplace) (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (22): ReLU (inplace) (23): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (25): ReLU (inplace) (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (27): ReLU (inplace) (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (29): ReLU (inplace) (30): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) ) (classifier): Sequential ( (0): Dropout (p = 0.5) (1): Linear (25088 -> 4096) (2): ReLU (inplace) (3): Dropout (p = 0.5) (4): Linear (4096 -> 4096) (5): ReLU (inplace) (6): Linear (4096 -> 1000) ) )正如 Kashyap 提到的，使用
state_dict方法可以得到不同层的权重。你可以通过这些层的信息自己创建一个函数来实现类似 Keras 的模型概要。希望这能帮到你。prosti - vote: 45
使用 torchsummary：
from torchsummary import summary如果没有的话，如下安装：
pip install torchsummary你可以试试，不过它需要你设置模型到 cuda 才能使用：
from torchsummary import summary help(summary) import torchvision.models as models alexnet = models.alexnet(pretrained=False) alexnet.cuda() summary(alexnet, (3, 224, 224)) print(alexnet)summary需要输入尺寸，将 batch_size 设为 -1 表示适用于任何 batch_size。如果设为
summary(alexnet, (3, 224, 224), 32)，则意味着使用batch_size=32。summary(model, input_size, batch_size=-1, device='cuda')输出
Help on function summary in module torchsummary.torchsummary: # summary(model, input_size, batch_size=-1, device='cuda') # ---------------------------------------------------------------- Layer (type) Output Shape Param # ================================================================ Conv2d-1 [32, 64, 55, 55] 23,296 ReLU-2 [32, 64, 55, 55] 0 MaxPool2d-3 [32, 64, 27, 27] 0 Conv2d-4 [32, 192, 27, 27] 307,392 ReLU-5 [32, 192, 27, 27] 0 MaxPool2d-6 [32, 192, 13, 13] 0 Conv2d-7 [32, 384, 13, 13] 663,936 ReLU-8 [32, 384, 13, 13] 0 Conv2d-9 [32, 256, 13, 13] 884,992 ReLU-10 [32, 256, 13, 13] 0 Conv2d-11 [32, 256, 13, 13] 590,080 ReLU-12 [32, 256, 13, 13] 0 MaxPool2d-13 [32, 256, 6, 6] 0 AdaptiveAvgPool2d-14 [32, 256, 6, 6] 0 Dropout-15 [32, 9216] 0 Linear-16 [32, 4096] 37,752,832 ReLU-17 [32, 4096] 0 Dropout-18 [32, 4096] 0 Linear-19 [32, 4096] 16,781,312 ReLU-20 [32, 4096] 0 Linear-21 [32, 1000] 4,097,000 ================================================================ Total params: 61,100,840 Trainable params: 61,100,840 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 18.38 Forward/backward pass size (MB): 268.12 Params size (MB): 233.08 Estimated Total Size (MB): 519.58 ---------------------------------------------------------------- AlexNet( (features): Sequential( (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2)) (1): ReLU(inplace) (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False) (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)) (4): ReLU(inplace) (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False) (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): ReLU(inplace) (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (9): ReLU(inplace) (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (11): ReLU(inplace) (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False) ) (avgpool): AdaptiveAvgPool2d(output_size=(6, 6)) (classifier): Sequential( (0): Dropout(p=0.5) (1): Linear(in_features=9216, out_features=4096, bias=True) (2): ReLU(inplace) (3): Dropout(p=0.5) (4): Linear(in_features=4096, out_features=4096, bias=True) (5): ReLU(inplace) (6): Linear(in_features=4096, out_features=1000, bias=True) ) )
Model summary in pytorch
Wasi Ahmad asked:
How do I print the summary of a model in PyTorch like the
model.summary()method does in Keras:
Pytorch 怎么像 Keras 的model.summary()获得一个模型概要？Model Summary: ____________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ==================================================================================================== input_1 (InputLayer) (None, 1, 15, 27) 0 ____________________________________________________________________________________________________ convolution2d_1 (Convolution2D) (None, 8, 15, 27) 872 input_1[0][0] ____________________________________________________________________________________________________ maxpooling2d_1 (MaxPooling2D) (None, 8, 7, 27) 0 convolution2d_1[0][0] ____________________________________________________________________________________________________ flatten_1 (Flatten) (None, 1512) 0 maxpooling2d_1[0][0] ____________________________________________________________________________________________________ dense_1 (Dense) (None, 1) 1513 flatten_1[0][0] ==================================================================================================== Total params: 2,385 Trainable params: 2,385 Non-trainable params: 0
Answers:
Shubham Chandel - vote: 213
Yes, you can get exact Keras representation, using the pytorch-summary package.
用 pytorch-summary 包可以实现 Keras 的效果。Example for VGG16:
VGG16 的例子：from torchvision import models from torchsummary import summary # vgg = models.vgg16() summary(vgg, (3, 224, 224)) # ---------------------------------------------------------------- Layer (type) Output Shape Param # ================================================================ Conv2d-1 [-1, 64, 224, 224] 1,792 ReLU-2 [-1, 64, 224, 224] 0 Conv2d-3 [-1, 64, 224, 224] 36,928 ReLU-4 [-1, 64, 224, 224] 0 MaxPool2d-5 [-1, 64, 112, 112] 0 Conv2d-6 [-1, 128, 112, 112] 73,856 ReLU-7 [-1, 128, 112, 112] 0 Conv2d-8 [-1, 128, 112, 112] 147,584 ReLU-9 [-1, 128, 112, 112] 0 MaxPool2d-10 [-1, 128, 56, 56] 0 Conv2d-11 [-1, 256, 56, 56] 295,168 ReLU-12 [-1, 256, 56, 56] 0 Conv2d-13 [-1, 256, 56, 56] 590,080 ReLU-14 [-1, 256, 56, 56] 0 Conv2d-15 [-1, 256, 56, 56] 590,080 ReLU-16 [-1, 256, 56, 56] 0 MaxPool2d-17 [-1, 256, 28, 28] 0 Conv2d-18 [-1, 512, 28, 28] 1,180,160 ReLU-19 [-1, 512, 28, 28] 0 Conv2d-20 [-1, 512, 28, 28] 2,359,808 ReLU-21 [-1, 512, 28, 28] 0 Conv2d-22 [-1, 512, 28, 28] 2,359,808 ReLU-23 [-1, 512, 28, 28] 0 MaxPool2d-24 [-1, 512, 14, 14] 0 Conv2d-25 [-1, 512, 14, 14] 2,359,808 ReLU-26 [-1, 512, 14, 14] 0 Conv2d-27 [-1, 512, 14, 14] 2,359,808 ReLU-28 [-1, 512, 14, 14] 0 Conv2d-29 [-1, 512, 14, 14] 2,359,808 ReLU-30 [-1, 512, 14, 14] 0 MaxPool2d-31 [-1, 512, 7, 7] 0 Linear-32 [-1, 4096] 102,764,544 ReLU-33 [-1, 4096] 0 Dropout-34 [-1, 4096] 0 Linear-35 [-1, 4096] 16,781,312 ReLU-36 [-1, 4096] 0 Dropout-37 [-1, 4096] 0 Linear-38 [-1, 1000] 4,097,000 ================================================================ Total params: 138,357,544 Trainable params: 138,357,544 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 0.57 Forward/backward pass size (MB): 218.59 Params size (MB): 527.79 Estimated Total Size (MB): 746.96 ----------------------------------------------------------------SpiderWasp42 - vote: 185
While you will not get as detailed information about the model as in Keras\' model.summary, simply printing the model will give you some idea about the different layers involved and their specifications.
虽然不能像 Keras 的model.summary()一样得到模型详细信息，但通过打印模型你也能得到不同层的信息。For instance:
例：from torchvision import models model = models.vgg16() print(model)The output in this case would be something as follows:
输出如下：VGG ( (features): Sequential ( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU (inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): ReLU (inplace) (4): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (6): ReLU (inplace) (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (8): ReLU (inplace) (9): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (11): ReLU (inplace) (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (13): ReLU (inplace) (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (15): ReLU (inplace) (16): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (18): ReLU (inplace) (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (20): ReLU (inplace) (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (22): ReLU (inplace) (23): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (25): ReLU (inplace) (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (27): ReLU (inplace) (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (29): ReLU (inplace) (30): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)) ) (classifier): Sequential ( (0): Dropout (p = 0.5) (1): Linear (25088 -> 4096) (2): ReLU (inplace) (3): Dropout (p = 0.5) (4): Linear (4096 -> 4096) (5): ReLU (inplace) (6): Linear (4096 -> 1000) ) )Now you could, as mentioned by Kashyap, use the
state_dictmethod to get the weights of the different layers. But using this listing of the layers would perhaps provide more direction is creating a helper function to get that Keras like model summary! Hope this helps!
正如 Kashyap 提到的，使用state_dict方法可以得到不同层的权重。你可以通过这些层的信息自己创建一个函数来实现类似 Keras 的模型概要。希望这能帮到你。prosti - vote: 45
In order to use torchsummary type:
使用 torchsummary：from torchsummary import summaryInstall it first if you don\'t have it.
如果没有的话，如下安装：pip install torchsummaryAnd then you can try it, but note for some reason it is not working unless I set model to cuda
alexnet.cuda:
你可以试试，不过它需要你设置模型到 cuda 才能使用：from torchsummary import summary help(summary) import torchvision.models as models alexnet = models.alexnet(pretrained=False) alexnet.cuda() summary(alexnet, (3, 224, 224)) print(alexnet)The
summarymust take the input size and batch size is set to -1 meaning any batch size we provide.
summary需要输入尺寸，将 batch_size 设为 -1 表示适用于任何 batch_size。If we set
summary(alexnet, (3, 224, 224), 32)this means use thebs=32.
如果设为summary(alexnet, (3, 224, 224), 32)，则意味着使用batch_size=32。summary(model, input_size, batch_size=-1, device='cuda')Out:
输出Help on function summary in module torchsummary.torchsummary: # summary(model, input_size, batch_size=-1, device='cuda') # ---------------------------------------------------------------- Layer (type) Output Shape Param # ================================================================ Conv2d-1 [32, 64, 55, 55] 23,296 ReLU-2 [32, 64, 55, 55] 0 MaxPool2d-3 [32, 64, 27, 27] 0 Conv2d-4 [32, 192, 27, 27] 307,392 ReLU-5 [32, 192, 27, 27] 0 MaxPool2d-6 [32, 192, 13, 13] 0 Conv2d-7 [32, 384, 13, 13] 663,936 ReLU-8 [32, 384, 13, 13] 0 Conv2d-9 [32, 256, 13, 13] 884,992 ReLU-10 [32, 256, 13, 13] 0 Conv2d-11 [32, 256, 13, 13] 590,080 ReLU-12 [32, 256, 13, 13] 0 MaxPool2d-13 [32, 256, 6, 6] 0 AdaptiveAvgPool2d-14 [32, 256, 6, 6] 0 Dropout-15 [32, 9216] 0 Linear-16 [32, 4096] 37,752,832 ReLU-17 [32, 4096] 0 Dropout-18 [32, 4096] 0 Linear-19 [32, 4096] 16,781,312 ReLU-20 [32, 4096] 0 Linear-21 [32, 1000] 4,097,000 ================================================================ Total params: 61,100,840 Trainable params: 61,100,840 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 18.38 Forward/backward pass size (MB): 268.12 Params size (MB): 233.08 Estimated Total Size (MB): 519.58 ---------------------------------------------------------------- AlexNet( (features): Sequential( (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2)) (1): ReLU(inplace) (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False) (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)) (4): ReLU(inplace) (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False) (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (7): ReLU(inplace) (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (9): ReLU(inplace) (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (11): ReLU(inplace) (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False) ) (avgpool): AdaptiveAvgPool2d(output_size=(6, 6)) (classifier): Sequential( (0): Dropout(p=0.5) (1): Linear(in_features=9216, out_features=4096, bias=True) (2): ReLU(inplace) (3): Dropout(p=0.5) (4): Linear(in_features=4096, out_features=4096, bias=True) (5): ReLU(inplace) (6): Linear(in_features=4096, out_features=1000, bias=True) ) )
共有 0 条评论