您好,登錄后才能下訂單哦!
這篇文章給大家分享的是有關Python基于Pytorch特征圖提取的示例分析的內容。小編覺得挺實用的,因此分享給大家做個參考,一起跟隨小編過來看看吧。
為了方便理解卷積神經網絡的運行過程,需要對卷積神經網絡的運行結果進行可視化的展示。
大致可分為如下步驟:
單個圖片的提取
神經網絡的構建
特征圖的提取
可視化展示
根據目標要求,需要對單個圖片進行卷積運算,但是Pytorch中讀取數據主要用到torch.utils.data.DataLoader類,因此我們需要編寫單個圖片的讀取程序
def get_picture(picture_dir, transform): ''' 該算法實現了讀取圖片,并將其類型轉化為Tensor ''' tmp = [] img = skimage.io.imread(picture_dir) tmp.append(img) img = skimage.io.imread('./picture/4.jpg') tmp.append(img) img256 = [skimage.transform.resize(img, (256, 256)) for img in tmp] img256 = np.asarray(img256) img256 = img256.astype(np.float32) return transform(img256[0])
注意: 神經網絡的輸入是四維形式,我們返回的圖片是三維形式,需要使用unsqueeze()插入一個維度
網絡的基于LeNet構建,不過為了方便展示,將其中的參數按照2562563進行的參數的修正
網絡構建如下:
class LeNet(nn.Module): ''' 該類繼承了torch.nn.Modul類 構建LeNet神經網絡模型 ''' def __init__(self): super(LeNet, self).__init__() # 第一層神經網絡,包括卷積層、線性激活函數、池化層 self.conv1 = nn.Sequential( nn.Conv2d(3, 32, 5, 1, 2), # input_size=(3*256*256),padding=2 nn.ReLU(), # input_size=(32*256*256) nn.MaxPool2d(kernel_size=2, stride=2), # output_size=(32*128*128) ) # 第二層神經網絡,包括卷積層、線性激活函數、池化層 self.conv2 = nn.Sequential( nn.Conv2d(32, 64, 5, 1, 2), # input_size=(32*128*128) nn.ReLU(), # input_size=(64*128*128) nn.MaxPool2d(2, 2) # output_size=(64*64*64) ) # 全連接層(將神經網絡的神經元的多維輸出轉化為一維) self.fc1 = nn.Sequential( nn.Linear(64 * 64 * 64, 128), # 進行線性變換 nn.ReLU() # 進行ReLu激活 ) # 輸出層(將全連接層的一維輸出進行處理) self.fc2 = nn.Sequential( nn.Linear(128, 84), nn.ReLU() ) # 將輸出層的數據進行分類(輸出預測值) self.fc3 = nn.Linear(84, 62) # 定義前向傳播過程,輸入為x def forward(self, x): x = self.conv1(x) x = self.conv2(x) # nn.Linear()的輸入輸出都是維度為一的值,所以要把多維度的tensor展平成一維 x = x.view(x.size()[0], -1) x = self.fc1(x) x = self.fc2(x) x = self.fc3(x) return x
直接上代碼:
class FeatureExtractor(nn.Module): def __init__(self, submodule, extracted_layers): super(FeatureExtractor, self).__init__() self.submodule = submodule self.extracted_layers = extracted_layers def forward(self, x): outputs = [] for name, module in self.submodule._modules.items(): # 目前不展示全連接層 if "fc" in name: x = x.view(x.size(0), -1) print(module) x = module(x) print(name) if name in self.extracted_layers: outputs.append(x) return outputs
可視化展示使用matplotlib
代碼如下:
# 特征輸出可視化 for i in range(32): ax = plt.subplot(6, 6, i + 1) ax.set_title('Feature {}'.format(i)) ax.axis('off') plt.imshow(x[0].data.numpy()[0,i,:,:],cmap='jet') plt.plot()
在此貼上完整代碼
import os import torch import torchvision as tv import torchvision.transforms as transforms import torch.nn as nn import torch.optim as optim import argparse import skimage.data import skimage.io import skimage.transform import numpy as np import matplotlib.pyplot as plt # 定義是否使用GPU device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # Load training and testing datasets. pic_dir = './picture/3.jpg' # 定義數據預處理方式(將輸入的類似numpy中arrary形式的數據轉化為pytorch中的張量(tensor)) transform = transforms.ToTensor() def get_picture(picture_dir, transform): ''' 該算法實現了讀取圖片,并將其類型轉化為Tensor ''' img = skimage.io.imread(picture_dir) img256 = skimage.transform.resize(img, (256, 256)) img256 = np.asarray(img256) img256 = img256.astype(np.float32) return transform(img256) def get_picture_rgb(picture_dir): ''' 該函數實現了顯示圖片的RGB三通道顏色 ''' img = skimage.io.imread(picture_dir) img256 = skimage.transform.resize(img, (256, 256)) skimage.io.imsave('./picture/4.jpg',img256) # 取單一通道值顯示 # for i in range(3): # img = img256[:,:,i] # ax = plt.subplot(1, 3, i + 1) # ax.set_title('Feature {}'.format(i)) # ax.axis('off') # plt.imshow(img) # r = img256.copy() # r[:,:,0:2]=0 # ax = plt.subplot(1, 4, 1) # ax.set_title('B Channel') # # ax.axis('off') # plt.imshow(r) # g = img256.copy() # g[:,:,0]=0 # g[:,:,2]=0 # ax = plt.subplot(1, 4, 2) # ax.set_title('G Channel') # # ax.axis('off') # plt.imshow(g) # b = img256.copy() # b[:,:,1:3]=0 # ax = plt.subplot(1, 4, 3) # ax.set_title('R Channel') # # ax.axis('off') # plt.imshow(b) # img = img256.copy() # ax = plt.subplot(1, 4, 4) # ax.set_title('image') # # ax.axis('off') # plt.imshow(img) img = img256.copy() ax = plt.subplot() ax.set_title('image') # ax.axis('off') plt.imshow(img) plt.show() class LeNet(nn.Module): ''' 該類繼承了torch.nn.Modul類 構建LeNet神經網絡模型 ''' def __init__(self): super(LeNet, self).__init__() # 第一層神經網絡,包括卷積層、線性激活函數、池化層 self.conv1 = nn.Sequential( nn.Conv2d(3, 32, 5, 1, 2), # input_size=(3*256*256),padding=2 nn.ReLU(), # input_size=(32*256*256) nn.MaxPool2d(kernel_size=2, stride=2), # output_size=(32*128*128) ) # 第二層神經網絡,包括卷積層、線性激活函數、池化層 self.conv2 = nn.Sequential( nn.Conv2d(32, 64, 5, 1, 2), # input_size=(32*128*128) nn.ReLU(), # input_size=(64*128*128) nn.MaxPool2d(2, 2) # output_size=(64*64*64) ) # 全連接層(將神經網絡的神經元的多維輸出轉化為一維) self.fc1 = nn.Sequential( nn.Linear(64 * 64 * 64, 128), # 進行線性變換 nn.ReLU() # 進行ReLu激活 ) # 輸出層(將全連接層的一維輸出進行處理) self.fc2 = nn.Sequential( nn.Linear(128, 84), nn.ReLU() ) # 將輸出層的數據進行分類(輸出預測值) self.fc3 = nn.Linear(84, 62) # 定義前向傳播過程,輸入為x def forward(self, x): x = self.conv1(x) x = self.conv2(x) # nn.Linear()的輸入輸出都是維度為一的值,所以要把多維度的tensor展平成一維 x = x.view(x.size()[0], -1) x = self.fc1(x) x = self.fc2(x) x = self.fc3(x) return x # 中間特征提取 class FeatureExtractor(nn.Module): def __init__(self, submodule, extracted_layers): super(FeatureExtractor, self).__init__() self.submodule = submodule self.extracted_layers = extracted_layers def forward(self, x): outputs = [] print(self.submodule._modules.items()) for name, module in self.submodule._modules.items(): if "fc" in name: print(name) x = x.view(x.size(0), -1) print(module) x = module(x) print(name) if name in self.extracted_layers: outputs.append(x) return outputs def get_feature(): # 輸入數據 img = get_picture(pic_dir, transform) # 插入維度 img = img.unsqueeze(0) img = img.to(device) # 特征輸出 net = LeNet().to(device) # net.load_state_dict(torch.load('./model/net_050.pth')) exact_list = ["conv1","conv2"] myexactor = FeatureExtractor(net, exact_list) x = myexactor(img) # 特征輸出可視化 for i in range(32): ax = plt.subplot(6, 6, i + 1) ax.set_title('Feature {}'.format(i)) ax.axis('off') plt.imshow(x[0].data.numpy()[0,i,:,:],cmap='jet') plt.show() # 訓練 if __name__ == "__main__": get_picture_rgb(pic_dir) # get_feature()
感謝各位的閱讀!關于“Python基于Pytorch特征圖提取的示例分析”這篇文章就分享到這里了,希望以上內容可以對大家有一定的幫助,讓大家可以學到更多知識,如果覺得文章不錯,可以把它分享出去讓更多的人看到吧!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。