PyTorch: 各种图像格式相互转化
我们一般在PyTorch或者Python中处理的图像无非这几种格式:
- PIL:使用Python自带图像处理库读取出来的图片格式;
- numpy:使用python-opencv库读取出来的图片格式;
- tensor:pytorch中训练时所采取的向量格式(当然也可以说图片).
注意,本文所述图片格式皆为RGB三通道,24-bit真彩色,也就是我们平常使用的图片形式。
下述代码均引用了:
import cv2
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()
PIL读取图片转化为Tensor
# 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PIL格式图片, 返回tensor变量
def PIL_to_tensor(image):
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
Tensor转化为PIL图片
# 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
直接展示Tensor格式图片
def imshow(tensor, title=None):
image = tensor.cpu().clone() # we clone the tensor to not do changes on it
image = image.squeeze(0) # remove the fake batch dimension
image = unloader(image)
plt.imshow(image)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
直接保存Tensor格式图片
def save_image(tensor, **para):
dir = 'results'
image = tensor.cpu().clone() # we clone the tensor to not do changes on it
image = image.squeeze(0) # remove the fake batch dimension
image = unloader(image)
if not osp.exists(dir):
os.makedirs(dir)
image.save('results_{}/s{}-c{}-l{}-e{}-sl{:4f}-cl{:4f}.jpg'
.format(num, para['style_weight'], para['content_weight'], para['lr'], para['epoch'],
para['style_loss'], para['content_loss']))
Numpy转化为Tensor
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
Tensor转化为Numpy
def tensor_to_np(tensor):
img = tensor.mul(255).byte()
img = img.cpu().numpy().squeeze(0).transpose((1, 2, 0))
return img
展示Numpy格式图片
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)
展示Tensor格式图片
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)
注意: 上面介绍的都是一张图片的转化,如果是n张图片一起的话,只需要修改一下相应代码即可。
# 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)