我们一般在pytorch或者python中处理的图像无非这几种格式:
import torch
from PIL import Image
import matplotlib.pyplot as plt
# loader使用torchvision中自带的transforms函数
loader = transforms.Compose([
transforms.ToTensor()])
unloader = transforms.ToPILImage()
# 输入图片地址
# 返回tensor变量
def image_loader(image_name):
image = Image.open(image_name).convert('RGB')
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
# 输入tensor变量
# 输出PIL格式图片
def tensor_to_PIL(tensor):
image = tensor.cpu().clone()
image = image.squeeze(0)
image = unloader(image)
return image
import cv2
import torch
import matplotlib.pyplot as plt
def tensor_to_np(tensor):
img = tensor.mul(255).byte()
img = img.cpu().numpy().squeeze(0).transpose((1, 2, 0))
return img
def toTensor(img):
assert type(img) == np.ndarray,'the img type is {}, but ndarry expected'.format(type(img))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = torch.from_numpy(img.transpose((2, 0, 1)))
return img.float().div(255).unsqueeze(0) # 255也可以改为256
def show_from_tensor(tensor, title=None):
img = tensor.clone()
img = tensor_to_np(img)
plt.figure()
plt.imshow(img)
if title is not None:
plt.title(title)
plt.pause(0.001)
def show_from_cv(img, title=None):
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
plt.figure()
plt.imshow(img)
if title is not None:
plt.title(title)
plt.pause(0.001)
以上代码都是单张图片格式的转换,若改为多张,则只需要稍微改动代码,以下为例:
# 将 N x H x W X C 的numpy格式图片转化为相应的tensor格式
def toTensor(img):
img = torch.from_numpy(img.transpose((0, 3, 1, 2)))
return img.float().div(255).unsqueeze(0)