ãŸããã³ãªãã®ãå匷äžã§ããããã³ãšããã®ã¯ããŸãã©ããç§ã«ãã¢ãã«ãªããªãã§ããããã®ããšããæå³ã§ãå匷ã®å¯Ÿè±¡ããã³ãšããæå³ã§ã¯ãªãã
äŸã«ãã£ãŠå¯Ÿè±¡ããããã ãªã®ã§ãæ°çã«è¡šç€ºããã«ããããããæ¥ä»ãããã®ãŒã£ãŠå ¬éããŠããŸããèªåçšã®ã¡ã¢ãšãããåæ§ã®ãã©ãã«ã«æ©ãŸãããŠãã人ãæ€çŽ¢ã§èŠã«æ¥ããããã³ãã«ãªãã°ãšããæå³ã§ã®å ¬éã§ããã€ãããããããééã£ãããšãã£ãšãããããã±ïŒããšãæ°ã¥ãã®æ¹ããããããã²ãæ瀺é¡ããŸãã
ãŒãããäœãDeep Learning âPythonã§åŠã¶ãã£ãŒãã©ãŒãã³ã°ã®çè«ãšå®è£
- äœè : æè€åº·æ¯
- åºç瀟/ã¡ãŒã«ãŒ: ãªã©ã€ãªãŒãžã£ãã³
- çºå£²æ¥: 2016/09/24
- ã¡ãã£ã¢: åè¡æ¬ïŒãœããã«ããŒïŒ
- ãã®ååãå«ãããã° (11件) ãèŠã
ãã©ãããã©ãŒã 㯠Windows10ãPython 3 ç³»ãã€ã³ã¹ããŒã«ããŠãGIT HUB ãããµã³ãã«ããã°ã©ã ãããŠã³ããŒãããŠã3ç« ã®éäžãŸã§ã¯ãµã³ãã«ããã°ã©ã ããµã¯ãµã¯åãããšã確èªããã
3ç« P75ã§ããµã³ãã«ããã°ã©ã ch03\mnist_show.py ãå®è¡ããŠMNISTç»åã衚瀺ãããããšãããšããã§ãã€ãŸããããMNISTç»åãšã¯ãªããããšããããšã¯ãæèšäºã§ã¯è§£èª¬ããŸãããæ€çŽ¢ããŠé©åãªèšäºããåç §ãã ããã
ãããªæããç§ã®ããœã³ã³ã¯ BMPãã¡ã€ã«ã Windowsãã©ããã¥ãŒã¢ãŒã«é¢é£ä»ããŠããŸãã
ããã§ã1ç« P19ã§ç»åã衚瀺ãããµã³ãã«ããã°ã©ã ch01\img_show.py ãåèã«ããŠã次ã®ããã«æ¹é ããŠã¿ãã
import sys, os
sys.path.append(os.pardir)
import numpy as np
from dataset.mnist import load_mnist
from PIL import Image
def img_show(img):
  pil_img = Image.fromarray(np.uint8(img))
  pil_img.show()(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True, normalize=False)
img = x_train[0]
label = t_train[0]
print(label)print(img.shape) # (784,)
img = img.reshape(28, 28)
print(img.shape) # (28, 28)import matplotlib.pyplot as plt
from matplotlib.image import imreadplt.imshow(img)
plt.show()
éæåã§è¡šç€ºããéšåã¯ãµã³ãã«ããã°ã©ã mnist_show.py ãç·ã§è¡šç€ºããéšå㯠img_show.py ããæµçšãããã®ã§ããã
å®è¡ãããšããµã€ãºã¯ã§ãããP75ã®æ¿ãçµµãšåããšæãããç»åã衚瀺ãããïŒ
ãªãããœãŒã¹ã³ãŒãäžã®èµ€åã§è¡šç€ºããæ°å â0â ã â1â ã«å€æŽãããšâŠ
ãšè¡šç€ºããããâ2âãâ3âãâ4âãâŠãšå€æŽãããšã衚瀺ãããæ°å㯠â4âãâ1âãâ9âãâŠãšå€ãã£ããåã£ãŠãŸããïŒïŒèª°ã«èšãïŒ
ãšããªããšããã£ãåŸã§ãããäžåºŠãµã³ãã«ããã°ã©ã  mnist_show.py ãããäžåºŠèµ°ããããâŠ
ãªã衚瀺ãããïŒïŒ ãœãŒã¹ã³ãŒãå€æŽããªãã§ããã®ãŸãŸåå®è¡ãããã ããªã®ã«ïŒïŒ
ãšã³ããªãŒã«ããåã«ãææã¡ã®ãã1å°ã®ããŒããœã§åãããã°ã©ã ãå®è¡ããŠãåãçŸè±¡ãåçŸãããããšã確èªããããªãã§ãããªããã¯ãä»ã®ãšããè¬ã§ããã
ã¹ãã³ãµãŒãªã³ã¯
Â