Python pytorch中的模型摘要
如何在PyTorch中打印模型摘要,就像Keras中的Python pytorch中的模型摘要,python,pytorch,Python,Pytorch,如何在PyTorch中打印模型摘要,就像Keras中的model.summary()方法一样: Model Summary: ____________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to
model.summary()
方法一样:
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
虽然您不会像Keras的model.summary中那样获得关于模型的详细信息,但简单地打印模型将让您了解所涉及的不同层及其规格 例如:
from torchvision import models
model = models.vgg16()
print(model)
本例中的输出如下所示:
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)
)
)
现在,如所述,您可以使用
state\u dict
方法获得不同层的权重。但使用这个层列表可能会提供更多的方向,即创建一个帮助函数来获得类似于Keras的模型摘要!希望这有帮助 这将显示模型的权重和参数(但不显示输出形状)
编辑:isaykatsman有一个pytorch PR来添加一个与keras完全相似的model.summary()
,最容易记住(不像keras那么漂亮):
这项工作还包括:
repr(model)
如果只需要参数的数量:
sum([param.nelement() for param in model.parameters()])
From:是的,您可以使用该软件包获得精确的Keras表示 VGG16的示例:
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
----------------------------------------------------------------
为模型类定义对象后,只需打印模型即可
class RNN(nn.Module):
def __init__(self, input_dim, embedding_dim, hidden_dim, output_dim):
super().__init__()
self.embedding = nn.Embedding(input_dim, embedding_dim)
self.rnn = nn.RNN(embedding_dim, hidden_dim)
self.fc = nn.Linear(hidden_dim, output_dim)
def forward():
...
model = RNN(input_dim, embedding_dim, hidden_dim, output_dim)
print(model)
要使用torchsummary类型:
from torchsummary import summary
如果没有,请先安装它
pip install torchsummary
然后您可以尝试它,但请注意,由于某种原因,除非我将model设置为cudaalexnet.cuda
,否则它不会工作:
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)
摘要
必须采用输入大小,并且批大小设置为-1表示我们提供的任何批大小
如果我们设置了summary(alexnet,(32224224),32)
这意味着使用bs=32
summary(model, input_size, batch_size=-1, device='cuda')
输出: 你可以用
from torchsummary import summary
您可以指定设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
您可以创建一个网络,如果您使用的是MNIST数据集,那么以下命令将起作用并向您显示摘要
model = Network().to(device)
summary(model,(1,28,28))
使用torchsummary的Keras类模型摘要:
from torchsummary import summary
summary(model, input_size=(3, 224, 224))
(以前的torchsummary
)包生成与Keras1类似的输出(对于给定的输入形状):2
来自torchinfo导入摘要的
model=ConvNet()
批量大小=16
摘要(型号,输入尺寸=(批次尺寸,1,28,28)
==========================================================================================
图层(类型:深度idx)输出形状参数#
==========================================================================================
├─Conv2d(conv1):1-1[5,10,24,24]260
├─Conv2d(conv2):1-2[5,20,8,8]5020
├─辍学2d(conv2_drop):1-3[5,20,8,8]--
├─线性(fc1):1-4[5,50]16050
├─线性(fc2):1-5[5,10]510
==========================================================================================
总参数:21840
可培训参数:21840
不可训练参数:0
总乘数加总(M):7.69
==========================================================================================
输入大小(MB):0.05
向前/向后传递大小(MB):0.91
参数大小(MB):0.09
估计总大小(MB):1.05
==========================================================================================
注意事项:
print(您的_型号)
提供的信息互补的信息,类似于Tensorflow的model.summary()
summary(my_model,(3,224,224),device='cpu')
将解决这个问题。您看到模块上的state_dict()方法了吗?它为您提供了模型的不同参数。没有直接的summary方法,但是可以使用state_dict()来形成一个方法方法所选答案现已过时,torchsummary
是更好的解决方案。torchsummary
已过时。请使用TylerYep提供的torchinfo
找到解决方案。摘要(model.cuda(),(INPUT_SHAPE))
有效。大家好。我是新手,但我如何知道模型所需的输入形状?3224224对所有模型都是真的吗?@adikshit,这是网络输入的尺寸,在本例中是来自ImageNet数据集的224x224 RGB图像,因此是(3224224)。更一般地说,对于2D输入,形状是(C、H、W)其中C=通道,H=高度,W=宽度,对于1D输入,它将是(C,L),其中C=通道,L=长度。此软件包的更新版本可以在相同的用法中找到,但不同的pip安装。torchsummary
已失效。请使用TylerYepHow中的torchinfo
这与三(3)不同吗上面建议使用torchsummary
?torchsummary
的旧答案已失效。请使用TyleryEPTH中的torchinfo
,PR已关闭。torchsummary
已失效。请使用TyleryEPTH中的torchinfo
无效。summary
既不是PyTorch,也不是Python函数。from torcinfo导入摘要
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = Network().to(device)
summary(model,(1,28,28))
from torchsummary import summary
summary(model, input_size=(3, 224, 224))