快捷導(dǎo)航

獲取Pytorch中間某一層權(quán)重或者特征的例子

更新時(shí)間：2019年08月17日 11:16:38 作者：DaneAI

今天小編就為大家分享一篇獲取Pytorch中間某一層權(quán)重或者特征的例子，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧

問(wèn)題:訓(xùn)練好的網(wǎng)絡(luò)模型想知道中間某一層的權(quán)重或者看看中間某一層的特征,如何處理呢?

1、獲取某一層權(quán)重,并保存到excel中;

以resnet18為例說(shuō)明:

import torch
import pandas as pd
import numpy as np
import torchvision.models as models

resnet18 = models.resnet18(pretrained=True)

parm={}
for name,parameters in resnet18.named_parameters():
  print(name,':',parameters.size())
  parm[name]=parameters.detach().numpy()

上述代碼將每個(gè)模塊參數(shù)存入parm字典中,parameters.detach().numpy()將tensor類型變量轉(zhuǎn)換成numpy array形式,方便后續(xù)存儲(chǔ)到表格中.輸出為：

conv1.weight : torch.Size([64, 3, 7, 7])
bn1.weight : torch.Size([64])
bn1.bias : torch.Size([64])
layer1.0.conv1.weight : torch.Size([64, 64, 3, 3])
layer1.0.bn1.weight : torch.Size([64])
layer1.0.bn1.bias : torch.Size([64])
layer1.0.conv2.weight : torch.Size([64, 64, 3, 3])
layer1.0.bn2.weight : torch.Size([64])
layer1.0.bn2.bias : torch.Size([64])
layer1.1.conv1.weight : torch.Size([64, 64, 3, 3])
layer1.1.bn1.weight : torch.Size([64])
layer1.1.bn1.bias : torch.Size([64])
layer1.1.conv2.weight : torch.Size([64, 64, 3, 3])
layer1.1.bn2.weight : torch.Size([64])
layer1.1.bn2.bias : torch.Size([64])
layer2.0.conv1.weight : torch.Size([128, 64, 3, 3])
layer2.0.bn1.weight : torch.Size([128])
layer2.0.bn1.bias : torch.Size([128])
layer2.0.conv2.weight : torch.Size([128, 128, 3, 3])
layer2.0.bn2.weight : torch.Size([128])
layer2.0.bn2.bias : torch.Size([128])
layer2.0.downsample.0.weight : torch.Size([128, 64, 1, 1])
layer2.0.downsample.1.weight : torch.Size([128])
layer2.0.downsample.1.bias : torch.Size([128])
layer2.1.conv1.weight : torch.Size([128, 128, 3, 3])
layer2.1.bn1.weight : torch.Size([128])
layer2.1.bn1.bias : torch.Size([128])
layer2.1.conv2.weight : torch.Size([128, 128, 3, 3])
layer2.1.bn2.weight : torch.Size([128])
layer2.1.bn2.bias : torch.Size([128])
layer3.0.conv1.weight : torch.Size([256, 128, 3, 3])
layer3.0.bn1.weight : torch.Size([256])
layer3.0.bn1.bias : torch.Size([256])
layer3.0.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.0.bn2.weight : torch.Size([256])
layer3.0.bn2.bias : torch.Size([256])
layer3.0.downsample.0.weight : torch.Size([256, 128, 1, 1])
layer3.0.downsample.1.weight : torch.Size([256])
layer3.0.downsample.1.bias : torch.Size([256])
layer3.1.conv1.weight : torch.Size([256, 256, 3, 3])
layer3.1.bn1.weight : torch.Size([256])
layer3.1.bn1.bias : torch.Size([256])
layer3.1.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.1.bn2.weight : torch.Size([256])
layer3.1.bn2.bias : torch.Size([256])
layer4.0.conv1.weight : torch.Size([512, 256, 3, 3])
layer4.0.bn1.weight : torch.Size([512])
layer4.0.bn1.bias : torch.Size([512])
layer4.0.conv2.weight : torch.Size([512, 512, 3, 3])
layer4.0.bn2.weight : torch.Size([512])
layer4.0.bn2.bias : torch.Size([512])
layer4.0.downsample.0.weight : torch.Size([512, 256, 1, 1])
layer4.0.downsample.1.weight : torch.Size([512])
layer4.0.downsample.1.bias : torch.Size([512])
layer4.1.conv1.weight : torch.Size([512, 512, 3, 3])
layer4.1.bn1.weight : torch.Size([512])
layer4.1.bn1.bias : torch.Size([512])
layer4.1.conv2.weight : torch.Size([512, 512, 3, 3])
layer4.1.bn2.weight : torch.Size([512])
layer4.1.bn2.bias : torch.Size([512])
fc.weight : torch.Size([1000, 512])
fc.bias : torch.Size([1000])

parm['layer1.0.conv1.weight'][0,0,:,:]

輸出為:

array([[ 0.05759342, -0.09511436, -0.02027232],
[-0.07455588, -0.799308 , -0.21283598],
[ 0.06557069, -0.09653367, -0.01211061]], dtype=float32)

利用如下函數(shù)將某一層的所有參數(shù)保存到表格中,數(shù)據(jù)維持卷積核特征大小,如3*3的卷積保存后還是3x3的.

def parm_to_excel(excel_name,key_name,parm):
with pd.ExcelWriter(excel_name) as writer:
[output_num,input_num,filter_size,_]=parm[key_name].size()
for i in range(output_num):
for j in range(input_num):
data=pd.DataFrame(parm[key_name][i,j,:,:].detach().numpy())
#print(data)
data.to_excel(writer,index=False,header=True,startrow=i*(filter_size+1),startcol=j*filter_size)

由于權(quán)重矩陣中有很多的值非常小,取出固定大小的值,并將全部權(quán)重寫入excel

counter=1
with pd.ExcelWriter('test1.xlsx') as writer:
  for key in parm_resnet50.keys():
    data=parm_resnet50[key].reshape(-1,1)
    data=data[data>0.001]
    
    data=pd.DataFrame(data,columns=[key])
    data.to_excel(writer,index=False,startcol=counter)
    counter+=1

2、獲取中間某一層的特性

重寫一個(gè)函數(shù),將需要輸出的層輸出即可.

def resnet_cifar(net,input_data):
  x = net.conv1(input_data)
  x = net.bn1(x)
  x = F.relu(x)
  x = net.layer1(x)
  x = net.layer2(x)
  x = net.layer3(x)
  x = net.layer4[0].conv1(x) #這樣就提取了layer4第一塊的第一個(gè)卷積層的輸出
  x=x.view(x.shape[0],-1)
  return x

model = models.resnet18()
x = resnet_cifar(model,input_data)

以上這篇獲取Pytorch中間某一層權(quán)重或者特征的例子就是小編分享給大家的全部?jī)?nèi)容了，希望能給大家一個(gè)參考，也希望大家多多支持腳本之家。

您可能感興趣的文章: