Pytorch统计参数网络参数数量方式

目录

• Pytorch统计参数网络参数数量
• Pytorch如何计算网络的参数量
• 总结

Pytorch统计参数网络参数数量

def get_parameter_number(net):
    total_num = sum(p.numel() for p in net.parameters())
    trainable_num = sum(p.numel() for p in net.parameters() if p.requires_grad)
    return {'Total': total_num, 'Trainable': trainable_num}

Pytorch如何计算网络的参数量

本文以 Dense block 为例，Pytorch 为 DLjs 框架，最终计算模块参数量方法如下：

import torch
import torch.nn as nn

class Norm_Conv(nn.Module):

  def __init__(self,in_channel):
 php   super(Norm_Conv,self).__init__()
    self.layers = nn.Sequential(
      nn.Conv2d(in_channel,in_channel,3,1,1),
      nn.ReLU(True),
      nn.BATchNorm2d(in_channel),
      nn.Conv2d(in_channel,in_channel,3,1,1),
      nn.ReLU(True),
      nn.BatchNorm2d(in_channel),
      nn.Conv2d(in_channel,in_channel,3,1,1),
      nn.ReLU(True),
      nn.BatchNorm2d(in_channel))
  def forward(self,input):
    out = self.layers(input)
开发者_Go开发    return out


class Densewww.devze.comBlock_Norm(nn.Module):
  def __init__(self,in_channel):
    super(DenpythonseBlock_Norm,self).__init__()

    self.first_layer = nn.Sequential(nn.Conv2d(in_channel,in_channel,3,1,1),
                    nn.ReLU(True),
                    nn.BatchNorm2d(in_channel))
    self.second_layer = nn.Sequential(nn.Conv2d(in_channel*2,in_channel,3,1,1),
                     nn.ReLU(True),
                     nn.BatchNorm2d(in_channel))
    javascriptself.third_layer = nn.Sequential(
      nn.Conv2d(in_channel*3,in_channel,3,1,1),
      nn.ReLU(True),
      nn.BatchNorm2d(in_channel))

  def forward(self,input):

    output1 = self.first_layer(input)
    output2 = self.second_layer(torch.cat((output1,input),dim=1))
    output3 = self.third_layer(torch.cat((input,output1,output2),dim=1))

    return output3

def count_param(model):
  param_count = 0
  for param in model.parameters():
    param_count += param.view(-1).size()[0]
  return param_count

# Get Parameter number of Network
in_channel = 128
net1 = Norm_Conv(in_channel)
print('Norm Conv parameter count is {}'.format(count_param(net1)))
net2 = DenseBlock_Norm(in_channel)
print('DenseBlock Norm parameter count is {}'.format(count_param(net2)))

最终结果如下

Norm Conv parameter count is 443520

DenseBlock Norm parameter count is 885888

总结

以上为个人经验，希望能给大家一个参考，也希望大家多多支持我们。