pytorch-图像预处理

最新推荐文章于 2023-01-07 22:08:44 发布

TYUT_xiaoming

最新推荐文章于 2023-01-07 22:08:44 发布

阅读量749

点赞数 4

分类专栏： pytorch

本文链接：https://blog.csdn.net/TYUT_xiaoming/article/details/103260876

版权

pytorch 专栏收录该内容

11 篇文章 1 订阅

订阅专栏

参考链接：https://blog.csdn.net/qq_34199326/article/details/84072505

img_ = img[:,:,::-1].transpose((2,0,1))

img是【h,w,channel】，这里的img[:,:,::-1]是将第三个维度channel从opencv的BGR转化为pytorch的RGB

transpose((2,0,1))的意思是将[height,width,channel]->[channel,height,width]

def get_test_input():
    img = cv2.imread("dog-cycle-car.png")
    img = cv2.resize(img, (416,416))          #Resize to the input dimension
    img_ =  img[:,:,::-1].transpose((2,0,1))  # BGR->RGB |  channel change
    img_ = img_[np.newaxis,:,:,:]/255.0     #Add a channel at 0 (for batch) | Normalise
    img_ = torch.from_numpy(img_).float()     #Convert to float
    img_ = Variable(img_)                     # Convert to Variable
    return img_