深度学习的特征提取和特征可视化

import matplotlib.pyplot as plt
import torch
from PIL import Image
import numpy as np
import sys
sys.path.append("..")
from torchvision import transforms,models
from torch import nn
# 对于给定的一个网络层的输出x,x为numpy格式的array,维度为[0, channels, width, height]
# %matplotlib inline

1.需要的包

def draw_features(width, height, channels,x,savename):
    '''
    x: 输入的array,某一层的网络层输出
    savename: 特征可视化的保存路径
    width, height: 分别表示可视化子图的个数,二者乘积等于channels
    '''
    fig = plt.figure(figsize=(32,32))
    fig.subplots_adjust(left=0.05, right=0.95, bottom=0.05, top=0.95, wspace=0.05, hspace=0.05)
    for i in range(channels):
        plt.subplot(height,width, i + 1)
        plt.axis('off')
        img = x[0, i, :, :]
        pmin = np.min(img)
        pmax = np.max(img)
        img = (img - pmin) / (pmax - pmin + 0.000001)