import deepsee_models
from util import util
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('-p0', '--path0', type=str, default='./imgs/ex_ref.png')
parser.add_argument('-p1', '--path1', type=str, default='./imgs/ex_p0.png')
parser.add_argument('--use_gpu',
action='store_true',
help='turn on flag to use GPU')
opt = parser.parse_args()
## Initializing the model
model = deepsee_models.PerceptualLoss(model='net-lin',
net='alex',
use_gpu=opt.use_gpu)
# Load images
img0 = util.im2tensor(util.load_image(opt.path0)) # RGB image from [-1,1]
img1 = util.im2tensor(util.load_image(opt.path1))
if (opt.use_gpu):
img0 = img0.cuda()
img1 = img1.cuda()
# Compute distance
dist01 = model.forward(img0, img1)
print('Distance: %.3f' % dist01)
import torch
import deepsee_models
from util import util
use_gpu = False # Whether to use GPU
spatial = True # Return a spatial map of perceptual distance.
# Linearly calibrated deepsee_models (LPIPS)
model = deepsee_models.PerceptualLoss(model='net-lin',
net='alex',
use_gpu=use_gpu,
spatial=spatial)
# Can also set net = 'squeeze' or 'vgg'
# Off-the-shelf uncalibrated networks
# model = deepsee_models.PerceptualLoss(model='net', net='alex', use_gpu=use_gpu, spatial=spatial)
# Can also set net = 'squeeze' or 'vgg'
# Low-level metrics
# model = deepsee_models.PerceptualLoss(model='L2', colorspace='Lab', use_gpu=use_gpu)
# model = deepsee_models.PerceptualLoss(model='ssim', colorspace='RGB', use_gpu=use_gpu)
## Example usage with dummy tensors
dummy_im0 = torch.zeros(1, 3, 64,
64) # image should be RGB, normalized to [-1,1]
dummy_im1 = torch.zeros(1, 3, 64, 64)
if (use_gpu):
dummy_im0 = dummy_im0.cuda()
dummy_im1 = dummy_im1.cuda()
dist = model.forward(dummy_im0, dummy_im1)
import deepsee_models
use_gpu = True
ref_path = './imgs/ex_ref.png'
pred_path = './imgs/ex_p1.png'
ref_img = scipy.misc.imread(ref_path).transpose(2, 0, 1) / 255.
pred_img = scipy.misc.imread(pred_path).transpose(2, 0, 1) / 255.
# Torchify
ref = Variable(torch.FloatTensor(ref_img)[None, :, :, :])
pred = Variable(torch.FloatTensor(pred_img)[None, :, :, :], requires_grad=True)
loss_fn = deepsee_models.PerceptualLoss(model='net-lin',
net='vgg',
use_gpu=use_gpu)
optimizer = torch.optim.Adam([
pred,
], lr=1e-3, betas=(0.9, 0.999))
import matplotlib.pyplot as plt
plt.ion()
fig = plt.figure(1)
ax = fig.add_subplot(131)
ax.imshow(ref_img.transpose(1, 2, 0))
ax.set_title('target')
ax = fig.add_subplot(133)
ax.imshow(pred_img.transpose(1, 2, 0))
ax.set_title('initialization')