- Practical Convolutional Neural Networks
- Mohit Sewak Md. Rezaul Karim Pradeep Pujari
- 209字
- 2021-06-24 18:58:53
Code for visualizing an image
Let's take a look at how an image can be visualized with the following code:
#import all required lib
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
from skimage.io import imread
from skimage.transform import resize
# Load a color image in grayscale
image = imread('sample_digit.png',as_grey=True)
image = resize(image,(28,28),mode='reflect')
print('This image is: ',type(image),
'with dimensions:', image.shape)
plt.imshow(image,cmap='gray')
We obtain the following image as a result:

def visualize_input(img, ax):
ax.imshow(img, cmap='gray')
width, height = img.shape
thresh = img.max()/2.5
for x in range(width):
for y in range(height):
ax.annotate(str(round(img[x][y],2)), xy=(y,x),
horizontalalignment='center',
verticalalignment='center',
color='white' if img[x][y]<thresh else 'black')
fig = plt.figure(figsize = (12,12))
ax = fig.add_subplot(111)
visualize_input(image, ax)
The following result is obtained:

In the previous chapter, we used an MLP-based approach to recognize images. There are two issues with that approach:
- It increases the number of parameters
- It only accepts vectors as input, that is, flattening a matrix to a vector
This means we must find a new way to process images, in which 2D information is not completely lost. CNNs address this issue. Furthermore, CNNs accept matrices as input. Convolutional layers preserve spatial structures. First, we define a convolution window, also called a filter, or kernel; then slide this over the image.
推薦閱讀
- 數據庫應用基礎教程(Visual FoxPro 9.0)
- 3D計算機視覺:原理、算法及應用
- 白話大數據與機器學習
- MATLAB Graphics and Data Visualization Cookbook
- 云原生數據中臺:架構、方法論與實踐
- Augmented Reality using Appcelerator Titanium Starter
- SAS金融數據挖掘與建模:系統方法與案例解析
- 新手學會計(2013-2014實戰升級版)
- Oracle 11g+ASP.NET數據庫系統開發案例教程
- 數據中心經營之道
- 云工作時代:科技進化必將帶來的新工作方式
- Learn Selenium
- 數據可視化五部曲
- 達夢數據庫集群
- SQL應用開發參考手冊