python、PyTorch影象讀取與numpy轉換例項
Tensor轉為numpy
np.array(Tensor)
numpy轉換為Tensor
torch.Tensor(numpy.darray)
PIL.Image.Image轉換成numpy
np.array(PIL.Image.Image)
numpy 轉換成PIL.Image.Image
Image.fromarray(numpy.ndarray)
首先需要保證numpy.ndarray 轉換成np.uint8型
numpy.astype(np.uint8),畫素值[0,255]。
同時灰度影象保證numpy.shape為(H,W),不能出現channels
這裡需要np.squeeze()。彩色圖象保證numpy.shape為(H,W,3)
之後Image.fromarray(numpy.ndarray)
PIL.Image.Image轉換成Tensor
torchvision.transfrom
img=Image.open('00381fa010_940422.tif').convert('L') import torchvision.transforms as transforms trans=transforms.Compose([transforms.ToTensor()]) a=trans(img)
Tensor轉化成PIL.Image.Image
先轉換成numpy,再轉換成PIL.Image.Image
灰度影象
img=Image.open('00381fa010_940422.tif').convert('L') import torchvision.transforms as transforms trans=transforms.Compose([transforms.ToTensor()]) a=trans(img) b=np.array(a) #b.shape (1,64,64) maxi=b.max() b=b*255./maxi b=b.transpose(1,2,0).astype(np.uint8) b=np.squeeze(b,axis=2) xx=Image.fromarray(b) xx
彩色圖象
img2=Image.open('00381fa010_940422.tif').convert('RGB') import torchvision.transforms as transforms trans=transforms.Compose([transforms.ToTensor()]) a=trans(img2) a=np.array(a) maxi=a.max() a=a/maxi*255 a=a.transpose(1,0).astype(np.uint8) b=Image.fromarray(a) b
python-opencv
import cv2 a=cv2.imread('00381fa010_940422.tif') #a.shape (64,3) cv2.imwrite('asd.jpg',a) Image.fromarray(a) b=cv2.imread('00381fa010_940422.tif',0)#b.shape (64,64) Image.fromarray(b)
cv2.imread()返回numpy.darray, 讀取灰度影象之後shape為(64,64),RGB影象的shape為(64,3),可直接用Image.fromarray()轉換成Image。
cv寫影象時,灰度影象shape可以為(H,W)或(H,1)。彩色影象(H,3)
要從numpy.ndarray得到PIL.Image.Image,灰度圖的shape必須為(H,W),彩色為(H,3)
對於Variable型別不能直接轉換成numpy.ndarray,需要用.data轉換
np.array(a.data)
以上這篇python、PyTorch影象讀取與numpy轉換例項就是小編分享給大家的全部內容了,希望能給大家一個參考,也希望大家多多支援我們。