def test_l1_loss(self):
jt_loss=jnn.L1Loss()
tc_loss=tnn.L1Loss()
output=np.random.randn(10,100).astype(np.float32)
target=np.random.randn(10,100).astype(np.float32)
jt_y=jt_loss(jt.array(output), jt.array(target))
tc_y=tc_loss(torch.from_numpy(output), torch.from_numpy(target))
assert np.allclose(jt_y.numpy(), tc_y.numpy())
img = img[0]
min_ = -1
max_ = 1
img = (img - min_) / (max_ - min_) * 255
img = img.transpose((1, 2, 0))
if C == 3:
img = img[:, :, ::-1]
cv2.imwrite(path, img)
os.makedirs("images/%s" % opt.dataset_name, exist_ok=True)
os.makedirs("checkpoints/%s" % opt.dataset_name, exist_ok=True)
# Loss functions
criterion_GAN = nn.BCELoss() # no lsgan
criterion_pixelwise = nn.L1Loss()
# Calculate output of image discriminator (PatchGAN)
patch = (1, opt.img_height // 2**4, opt.img_width // 2**4)
# Initialize generator and discriminator
G_global = GeneratorResNet(in_channels=opt.in_channels,
out_channels=opt.out_channels)
G_l_eyel = GeneratorResNet(in_channels=opt.in_channels,
out_channels=opt.out_channels,
num_res_blocks=3)
G_l_eyer = GeneratorResNet(in_channels=opt.in_channels,
out_channels=opt.out_channels,
num_res_blocks=3)
G_l_nose = GeneratorResNet(in_channels=opt.in_channels,
out_channels=opt.out_channels,
min_ = img.min()
max_ = img.max()
img = (img - min_) / (max_ - min_) * 255
img = img.transpose((1, 2, 0))
if C == 3:
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
cv2.imwrite(path, img)
# Calculate output of image discriminator (PatchGAN)
patch_h, patch_w = int(opt.mask_size / 2**3), int(opt.mask_size / 2**3)
patch = (1, patch_h, patch_w)
# Loss function
adversarial_loss = nn.MSELoss()
pixelwise_loss = nn.L1Loss()
# Initialize generator and discriminator
generator = Generator(channels=opt.channels)
discriminator = Discriminator(channels=opt.channels)
# Dataset loader
transforms_ = [
transform.Resize((opt.img_size, opt.img_size), mode=Image.BICUBIC),
transform.ImageNormalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
]
dataloader = ImageDataset("../../data/%s" % opt.dataset_name,
transforms_=transforms_).set_attrs(
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.n_cpu,
[img, img2[:, W * ncol * i:W * ncol * (i + 1), :]], axis=2)
min_ = img.min()
max_ = img.max()
img = (img - min_) / (max_ - min_) * 255
img = img.transpose((1, 2, 0))
if C == 3:
# img = img[:,:,::-1]
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
cv2.imwrite(path, img)
c_dim = len(opt.selected_attrs)
img_shape = (opt.channels, opt.img_height, opt.img_width)
# Loss functions
criterion_cycle = nn.L1Loss()
bce_with_logits_loss = nn.BCEWithLogitsLoss(size_average=False)
def criterion_cls(logit, target):
return bce_with_logits_loss(logit, target) / logit.size(0)
# Loss weights
lambda_cls = 1
lambda_rec = 10
lambda_gp = 10
# Initialize generator and discriminator
generator = GeneratorResNet(img_shape=img_shape,
res_blocks=opt.residual_blocks,
