Pytorch查看模型的参数量和计算量

1. stat

缺点：仅支持单输入模型

• Example

import torch.nn as nn
import torch.nn.functional as F
from torchstat import stat


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)


model = Net()
# [C, H, W]，不需要B维度
stat(model, (1, 28, 28))

2. thop

支持多输入网络

• Example

import torch
import torch.nn as nn
import torch.nn.functional as F
import thop


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)


model = Net()
x = torch.randn((1, 1, 28, 28))
flops, params = thop.profile(model, inputs=(x, ))
# 多输入则为
# flops, params = thop.profile(model, inputs=(x, y, z))
flops, params = thop.clever_format([flops, params], '%.3f')
print('flops:', flops)
print('params:', params)

3. ptflops

没试过支不支持多输入

• Example

import torch
import torch.nn as nn
import torch.nn.functional as F
from ptflops import get_model_complexity_info


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)


model = Net()
flops, params = get_model_complexity_info(model, (1, 28, 28), as_strings=False, print_per_layer_stat=True)
print('flops:', flops)
print('params:', params)

4. pytorch_model_summary

缺点：只能看参数量

• Example

import torch
import torch.nn as nn
import torch.nn.functional as F
from pytorch_model_summary import summary


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)


# show input shape
print(summary(Net(), torch.zeros((1, 1, 28, 28)), show_input=True))

# show output shape
print(summary(Net(), torch.zeros((1, 1, 28, 28)), show_input=False))

# show output shape and hierarchical view of net
print(summary(Net(), torch.zeros((1, 1, 28, 28)), show_input=False, show_hierarchical=True))