def main(args):
pydiffvg.set_device(th.device('cuda:1'))
# Load SVG
svg_path = os.path.join(args.svg_path)
save_svg_path = svg_path.replace('.svg', '_resave.svg')
canvas_width, canvas_height, shapes, shape_groups = pydiffvg.svg_to_scene(
svg_path)
print("canvas_width", canvas_width)
print("canvas_height", canvas_height)
print("shapes", shapes)
for shape in shapes:
print("num_control_points", shape.num_control_points.size(),
shape.num_control_points)
print("points", shape.points.size(), shape.points)
print("is_closed", shape.is_closed)
print("stroke_width", shape.stroke_width.size(), shape.stroke_width)
print("id", shape.id)
print("use_distance_approx", shape.use_distance_approx)
print("shape_groups", shape_groups)
pydiffvg.save_svg_paths_only(save_svg_path, canvas_width, canvas_height,
shapes, shape_groups)
# Save initial state
ref = render(canvas_width, canvas_height, shapes, shape_groups)
def main(args):
pydiffvg.set_device(th.device('cuda:1'))
# Load SVG
svg = os.path.join(args.svg)
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(svg)
# Save initial state
ref = render(canvas_width, canvas_height, shapes, shape_groups)
pydiffvg.imwrite(ref.cpu(), args.out, gamma=2.2)
def main(svg_dirs):
pydiffvg.set_device(th.device('cuda:1'))
assert os.path.exists(svg_dirs)
svg_files = os.listdir(svg_dirs)
for svg_file in svg_files:
if '.svg' not in svg_file:
continue
svg_file_path = os.path.join(svg_dirs, svg_file)
out_file_path = svg_file_path.replace('.svg', '.png')
# Load SVG
canvas_width, canvas_height, shapes, shape_groups = pydiffvg.svg_to_scene(svg_file_path)
# Save initial state
ref = render(canvas_width, canvas_height, shapes, shape_groups)
pydiffvg.imwrite(ref.cpu(), out_file_path, gamma=2.2)
def gen_func(self):
canvas_width, canvas_height, shapes, shape_groups = pydiffvg.svg_to_scene(self.input_path)
new_shapes = list()
new_groups = list()
for dx in range(0, self.multiplier_x):
for dy in range(0, self.multiplier_y):
for i in range(len(shapes)):
new_shape = build_translated_path(shapes[i], dy * canvas_height, dx * canvas_width)
new_shapes.append(new_shape)
path_group = pydiffvg.ShapeGroup(shape_ids=torch.tensor([len(new_shapes) - 1]), fill_color=None,
stroke_color=torch.tensor(self.stroke_color))
new_groups.append(path_group)
def gen():
return new_shapes, new_groups
return gen
def main(target_path, svg_path, output_dir, num_iter=1000, use_lpips_loss=False):
perception_loss = ttools.modules.LPIPS().to(pydiffvg.get_device())
target = torch.from_numpy(skimage.io.imread(target_path, as_gray=False, pilmode="RGB")).to(torch.float32) / 255.0
print("target", target.size())
target = target.pow(gamma)
target = target.to(pydiffvg.get_device())
target = target.unsqueeze(0)
target = target.permute(0, 3, 1, 2) # NHWC -> NCHW
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(svg_path)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width, canvas_height, shapes, shape_groups)
render = pydiffvg.RenderFunction.apply
img = render(canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None, # bg
*scene_args)
# The output image is in linear RGB space. Do Gamma correction before saving the image.
pydiffvg.imwrite(img.cpu(), f'{output_dir}/init.png', gamma=gamma)
points_vars = []
for path in shapes:
path.points.requires_grad = True
points_vars.append(path.points)
color_vars = {}
for group in shape_groups:
group.fill_color.requires_grad = True
color_vars[group.fill_color.data_ptr()] = group.fill_color
# color_vars = list(color_vars.values())
# Optimize
points_optim = torch.optim.Adam(points_vars, lr=0.1)
# color_optim = torch.optim.Adam(color_vars, lr=0.01)
# Adam iterations.
for t in range(num_iter):
print('iteration:', t)
points_optim.zero_grad()
# color_optim.zero_grad()
# Forward pass: render the image.
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width, canvas_height, shapes, shape_groups)
img = render(canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None, # bg
*scene_args)
# Compose img with white background
img = img[:, :, 3:4] * img[:, :, :3] + torch.ones(img.shape[0], img.shape[1], 3, device=pydiffvg.get_device()) * (1 - img[:, :, 3:4])
# Save the intermediate render.
pydiffvg.imwrite(img.cpu(), f'{output_dir}/iter_{t}.png', gamma=gamma)
img = img[:, :, :3]
# Convert img from HWC to NCHW
img = img.unsqueeze(0)
img = img.permute(0, 3, 1, 2) # NHWC -> NCHW
# print(img.size())
# print(target.size())
if use_lpips_loss:
loss = perception_loss(img, target)
else:
loss = (img - target).pow(2).mean()
print('render loss:', loss.item())
# Backpropagate the gradients.
loss.backward()
# Take a gradient descent step.
points_optim.step()
# color_optim.step()
for group in shape_groups:
group.fill_color.data.clamp_(0.0, 1.0)
if t % 10 == 0 or t == num_iter - 1:
pydiffvg.save_svg_paths_only(f'{output_dir}/iter_{t}.svg',
canvas_width, canvas_height, shapes, shape_groups)
# Render the final result.
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width, canvas_height, shapes, shape_groups)
img = render(canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None, # bg
*scene_args)
# Save the intermediate render.
pydiffvg.imwrite(img.cpu(), f'{output_dir}/final.png', gamma=gamma)
# Convert the intermediate renderings to a video.
from subprocess import call
call(["ffmpeg", "-framerate", "24", "-i",
f"{output_dir}/iter_%d.png", "-vb", "20M",
f"{output_dir}/out.mp4"])
def main(args):
pydiffvg.set_use_gpu(torch.cuda.is_available())
canvas_width, canvas_height, shapes, shape_groups = pydiffvg.svg_to_scene(
args.content_file)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width, canvas_height, shapes, shape_groups)
render = pydiffvg.RenderFunction.apply
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None,
*scene_args)
# Transform to gamma space
pydiffvg.imwrite(img.cpu(), 'results/style_transfer/init.png', gamma=1.0)
# HWC -> NCHW
img = img.unsqueeze(0)
img = img.permute(0, 3, 1, 2) # NHWC -> NCHW
loader = transforms.Compose([transforms.ToTensor()
]) # transform it into a torch tensor
def image_loader(image_name):
image = Image.open(image_name)
# fake batch dimension required to fit network's input dimensions
image = loader(image).unsqueeze(0)
return image.to(pydiffvg.get_device(), torch.float)
style_img = image_loader(args.style_img)
# alpha blend content with a gray background
content_img = img[:, :3, :, :] * img[:, 3, :, :] + \
0.5 * torch.ones([1, 3, img.shape[2], img.shape[3]]) * \
(1 - img[:, 3, :, :])
assert style_img.size() == content_img.size(), \
"we need to import style and content images of the same size"
# unloader = transforms.ToPILImage() # reconvert into PIL image
class ContentLoss(nn.Module):
def __init__(
self,
target,
):
super(ContentLoss, self).__init__()
# we 'detach' the target content from the tree used
# to dynamically compute the gradient: this is a stated value,
# not a variable. Otherwise the forward method of the criterion
# will throw an error.
self.target = target.detach()
def forward(self, input):
self.loss = F.mse_loss(input, self.target)
return input
def gram_matrix(input):
a, b, c, d = input.size() # a=batch size(=1)
# b=number of feature maps
# (c,d)=dimensions of a f. map (N=c*d)
features = input.view(a * b, c * d) # resise F_XL into \hat F_XL
G = torch.mm(features, features.t()) # compute the gram product
# we 'normalize' the values of the gram matrix
# by dividing by the number of element in each feature maps.
return G.div(a * b * c * d)
class StyleLoss(nn.Module):
def __init__(self, target_feature):
super(StyleLoss, self).__init__()
self.target = gram_matrix(target_feature).detach()
def forward(self, input):
G = gram_matrix(input)
self.loss = F.mse_loss(G, self.target)
return input
device = pydiffvg.get_device()
cnn = models.vgg19(pretrained=True).features.to(device).eval()
cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406]).to(device)
cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225]).to(device)
# create a module to normalize input image so we can easily put it in a
# nn.Sequential
class Normalization(nn.Module):
def __init__(self, mean, std):
super(Normalization, self).__init__()
# .view the mean and std to make them [C x 1 x 1] so that they can
# directly work with image Tensor of shape [B x C x H x W].
# B is batch size. C is number of channels. H is height and W is width.
self.mean = mean.clone().view(-1, 1, 1)
self.std = std.clone().view(-1, 1, 1)
def forward(self, img):
# normalize img
return (img - self.mean) / self.std
# desired depth layers to compute style/content losses :
content_layers_default = ['conv_4']
style_layers_default = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']
def get_style_model_and_losses(cnn,
normalization_mean,
normalization_std,
style_img,
content_img,
content_layers=content_layers_default,
style_layers=style_layers_default):
cnn = copy.deepcopy(cnn)
# normalization module
normalization = Normalization(normalization_mean,
normalization_std).to(device)
# just in order to have an iterable access to or list of content/syle
# losses
content_losses = []
style_losses = []
# assuming that cnn is a nn.Sequential, so we make a new nn.Sequential
# to put in modules that are supposed to be activated sequentially
model = nn.Sequential(normalization)
i = 0 # increment every time we see a conv
for layer in cnn.children():
if isinstance(layer, nn.Conv2d):
i += 1
name = 'conv_{}'.format(i)
elif isinstance(layer, nn.ReLU):
name = 'relu_{}'.format(i)
# The in-place version doesn't play very nicely with the ContentLoss
# and StyleLoss we insert below. So we replace with out-of-place
# ones here.
layer = nn.ReLU(inplace=False)
elif isinstance(layer, nn.MaxPool2d):
name = 'pool_{}'.format(i)
elif isinstance(layer, nn.BatchNorm2d):
name = 'bn_{}'.format(i)
else:
raise RuntimeError('Unrecognized layer: {}'.format(
layer.__class__.__name__))
model.add_module(name, layer)
if name in content_layers:
# add content loss:
target = model(content_img).detach()
content_loss = ContentLoss(target)
model.add_module("content_loss_{}".format(i), content_loss)
content_losses.append(content_loss)
if name in style_layers:
# add style loss:
target_feature = model(style_img).detach()
style_loss = StyleLoss(target_feature)
model.add_module("style_loss_{}".format(i), style_loss)
style_losses.append(style_loss)
# now we trim off the layers after the last content and style losses
for i in range(len(model) - 1, -1, -1):
if isinstance(model[i], ContentLoss) or isinstance(
model[i], StyleLoss):
break
model = model[:(i + 1)]
return model, style_losses, content_losses
def run_style_transfer(cnn,
normalization_mean,
normalization_std,
content_img,
style_img,
canvas_width,
canvas_height,
shapes,
shape_groups,
num_steps=500,
style_weight=5000,
content_weight=1):
"""Run the style transfer."""
print('Building the style transfer model..')
model, style_losses, content_losses = get_style_model_and_losses(
cnn, normalization_mean, normalization_std, style_img, content_img)
point_params = []
color_params = []
stroke_width_params = []
for shape in shapes:
if isinstance(shape, pydiffvg.Path):
point_params.append(shape.points.requires_grad_())
stroke_width_params.append(shape.stroke_width.requires_grad_())
for shape_group in shape_groups:
if isinstance(shape_group.fill_color, torch.Tensor):
color_params.append(shape_group.fill_color.requires_grad_())
elif isinstance(shape_group.fill_color, pydiffvg.LinearGradient):
point_params.append(
shape_group.fill_color.begin.requires_grad_())
point_params.append(
shape_group.fill_color.end.requires_grad_())
color_params.append(
shape_group.fill_color.stop_colors.requires_grad_())
if isinstance(shape_group.stroke_color, torch.Tensor):
color_params.append(shape_group.stroke_color.requires_grad_())
elif isinstance(shape_group.stroke_color, pydiffvg.LinearGradient):
point_params.append(
shape_group.stroke_color.begin.requires_grad_())
point_params.append(
shape_group.stroke_color.end.requires_grad_())
color_params.append(
shape_group.stroke_color.stop_colors.requires_grad_())
point_optimizer = optim.Adam(point_params, lr=1.0)
color_optimizer = optim.Adam(color_params, lr=0.01)
stroke_width_optimizers = optim.Adam(stroke_width_params, lr=0.1)
print('Optimizing..')
run = [0]
while run[0] <= num_steps:
point_optimizer.zero_grad()
color_optimizer.zero_grad()
stroke_width_optimizers.zero_grad()
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width, canvas_height, shapes, shape_groups)
render = pydiffvg.RenderFunction.apply
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None,
*scene_args)
# alpha blend img with a gray background
img = img[:, :, :3] * img[:, :, 3:4] + \
0.5 * torch.ones([img.shape[0], img.shape[1], 3]) * \
(1 - img[:, :, 3:4])
pydiffvg.imwrite(img.cpu(),
'results/style_transfer/step_{}.png'.format(
run[0]),
gamma=1.0)
# HWC to NCHW
img = img.permute([2, 0, 1]).unsqueeze(0)
model(img)
style_score = 0
content_score = 0
for sl in style_losses:
style_score += sl.loss
for cl in content_losses:
content_score += cl.loss
style_score *= style_weight
content_score *= content_weight
loss = style_score + content_score
loss.backward()
run[0] += 1
if run[0] % 1 == 0:
print("run {}:".format(run))
print('Style Loss : {:4f} Content Loss: {:4f}'.format(
style_score.item(), content_score.item()))
print()
point_optimizer.step()
color_optimizer.step()
stroke_width_optimizers.step()
for color in color_params:
color.data.clamp_(0, 1)
for w in stroke_width_params:
w.data.clamp_(0.5, 4.0)
return shapes, shape_groups
shapes, shape_groups = run_style_transfer(cnn, cnn_normalization_mean,
cnn_normalization_std,
content_img, style_img,
canvas_width, canvas_height,
shapes, shape_groups)
scene_args = pydiffvg.RenderFunction.serialize_scene(shapes, shape_groups)
render = pydiffvg.RenderFunction.apply
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None,
*scene_args)
# Transform to gamma space
pydiffvg.imwrite(img.cpu(), 'results/style_transfer/output.png', gamma=1.0)
def main(args):
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(args.svg_file)
w = int(canvas_width * args.size_scale)
h = int(canvas_height * args.size_scale)
pfilter = pydiffvg.PixelFilter(type=diffvg.FilterType.box,
radius=torch.tensor(0.5))
use_prefiltering = False
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
num_samples_x = 16
num_samples_y = 16
render = pydiffvg.RenderFunction.apply
img = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None,
*scene_args)
pydiffvg.imwrite(img.cpu(),
'results/finite_difference_comp/img.png',
gamma=1.0)
epsilon = 0.1
def perturb_scene(axis, epsilon):
shapes[2].points[:, axis] += epsilon
# for s in shapes:
# if isinstance(s, pydiffvg.Circle):
# s.center[axis] += epsilon
# elif isinstance(s, pydiffvg.Ellipse):
# s.center[axis] += epsilon
# elif isinstance(s, pydiffvg.Path):
# s.points[:, axis] += epsilon
# elif isinstance(s, pydiffvg.Polygon):
# s.points[:, axis] += epsilon
# elif isinstance(s, pydiffvg.Rect):
# s.p_min[axis] += epsilon
# s.p_max[axis] += epsilon
# for s in shape_groups:
# if isinstance(s.fill_color, pydiffvg.LinearGradient):
# s.fill_color.begin[axis] += epsilon
# s.fill_color.end[axis] += epsilon
perturb_scene(0, epsilon)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
render = pydiffvg.RenderFunction.apply
img0 = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None,
*scene_args)
forward_diff = (img0 - img) / (epsilon)
forward_diff = forward_diff.sum(axis=2)
x_diff_max = 1.5
x_diff_min = -1.5
print(forward_diff.max())
print(forward_diff.min())
forward_diff = cm.viridis(
normalize(forward_diff, x_diff_min, x_diff_max).cpu().numpy())
pydiffvg.imwrite(
forward_diff,
'results/finite_difference_comp/shared_edge_forward_diff.png',
gamma=1.0)
perturb_scene(0, -2 * epsilon)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
img1 = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None,
*scene_args)
backward_diff = (img - img1) / (epsilon)
backward_diff = backward_diff.sum(axis=2)
print(backward_diff.max())
print(backward_diff.min())
backward_diff = cm.viridis(
normalize(backward_diff, x_diff_min, x_diff_max).cpu().numpy())
pydiffvg.imwrite(
backward_diff,
'results/finite_difference_comp/shared_edge_backward_diff.png',
gamma=1.0)
perturb_scene(0, epsilon)
num_samples_x = 4
num_samples_y = 4
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
render_grad = pydiffvg.RenderFunction.render_grad
img_grad = render_grad(
torch.ones(h, w, 4),
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
*scene_args)
print(img_grad[:, :, 0].max())
print(img_grad[:, :, 0].min())
x_diff = cm.viridis(
normalize(img_grad[:, :, 0], x_diff_min, x_diff_max).cpu().numpy())
pydiffvg.imwrite(x_diff,
'results/finite_difference_comp/ours_x_diff.png',
gamma=1.0)
def main(args):
case_name = args.svg_file.split('/')[-1].split('.')[0]
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(args.svg_file)
w = int(canvas_width * args.size_scale)
h = int(canvas_height * args.size_scale)
print(w, h)
curve_counts = 0
for s in shapes:
if isinstance(s, pydiffvg.Circle):
curve_counts += 1
elif isinstance(s, pydiffvg.Ellipse):
curve_counts += 1
elif isinstance(s, pydiffvg.Path):
curve_counts += len(s.num_control_points)
elif isinstance(s, pydiffvg.Polygon):
curve_counts += len(s.points) - 1
if s.is_closed:
curve_counts += 1
elif isinstance(s, pydiffvg.Rect):
curve_counts += 1
print('curve_counts:', curve_counts)
pfilter = pydiffvg.PixelFilter(type=diffvg.FilterType.box,
radius=torch.tensor(0.5))
use_prefiltering = args.use_prefiltering
print('use_prefiltering:', use_prefiltering)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
num_samples_x = args.num_spp
num_samples_y = args.num_spp
if (use_prefiltering):
num_samples_x = 1
num_samples_y = 1
render = pydiffvg.RenderFunction.apply
img = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None, # background_image
*scene_args)
pydiffvg.imwrite(
img.cpu(),
f'results/finite_difference_comp/{case_name}_{use_prefiltering}/img.png',
gamma=1.0)
epsilon = 0.1
def perturb_scene(axis, epsilon):
for s in shapes:
if isinstance(s, pydiffvg.Circle):
s.center[axis] += epsilon
elif isinstance(s, pydiffvg.Ellipse):
s.center[axis] += epsilon
elif isinstance(s, pydiffvg.Path):
s.points[:, axis] += epsilon
elif isinstance(s, pydiffvg.Polygon):
s.points[:, axis] += epsilon
elif isinstance(s, pydiffvg.Rect):
s.p_min[axis] += epsilon
s.p_max[axis] += epsilon
for s in shape_groups:
if isinstance(s.fill_color, pydiffvg.LinearGradient):
s.fill_color.begin[axis] += epsilon
s.fill_color.end[axis] += epsilon
perturb_scene(0, epsilon)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
render = pydiffvg.RenderFunction.apply
img0 = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None, # background_image
*scene_args)
perturb_scene(0, -2 * epsilon)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
img1 = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None, # background_image
*scene_args)
x_diff = (img0 - img1) / (2 * epsilon)
x_diff = x_diff.sum(axis=2)
x_diff_max = x_diff.max() * args.clamping_factor
x_diff_min = x_diff.min() * args.clamping_factor
print(x_diff.max())
print(x_diff.min())
x_diff = cm.viridis(
normalize(x_diff, x_diff_min, x_diff_max).cpu().numpy())
pydiffvg.imwrite(
x_diff,
f'results/finite_difference_comp//{case_name}_{use_prefiltering}/finite_x_diff.png',
gamma=1.0)
perturb_scene(0, epsilon)
perturb_scene(1, epsilon)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
render = pydiffvg.RenderFunction.apply
img0 = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None, # background_image
*scene_args)
perturb_scene(1, -2 * epsilon)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
img1 = render(
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None, # background_image
*scene_args)
y_diff = (img0 - img1) / (2 * epsilon)
y_diff = y_diff.sum(axis=2)
y_diff_max = y_diff.max() * args.clamping_factor
y_diff_min = y_diff.min() * args.clamping_factor
y_diff = cm.viridis(
normalize(y_diff, y_diff_min, y_diff_max).cpu().numpy())
pydiffvg.imwrite(
y_diff,
f'results/finite_difference_comp/{case_name}_{use_prefiltering}/finite_y_diff.png',
gamma=1.0)
perturb_scene(1, epsilon)
scene_args = pydiffvg.RenderFunction.serialize_scene(
canvas_width,
canvas_height,
shapes,
shape_groups,
filter=pfilter,
use_prefiltering=use_prefiltering)
render_grad = pydiffvg.RenderFunction.render_grad
img_grad = render_grad(
torch.ones(h, w, 4, device=pydiffvg.get_device()),
w, # width
h, # height
num_samples_x, # num_samples_x
num_samples_y, # num_samples_y
0, # seed
None, # background_image
*scene_args)
print(img_grad[:, :, 0].max())
print(img_grad[:, :, 0].min())
x_diff = cm.viridis(
normalize(img_grad[:, :, 0], x_diff_min, x_diff_max).cpu().numpy())
y_diff = cm.viridis(
normalize(img_grad[:, :, 1], y_diff_min, y_diff_max).cpu().numpy())
pydiffvg.imwrite(
x_diff,
f'results/finite_difference_comp/{case_name}_{use_prefiltering}/ours_x_diff.png',
gamma=1.0)
pydiffvg.imwrite(
y_diff,
f'results/finite_difference_comp/{case_name}_{use_prefiltering}/ours_y_diff.png',
gamma=1.0)
def main():
pydiffvg.set_device(th.device('cuda:1'))
# Load SVG
svg = os.path.join("imgs", "peppers.svg")
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(svg)
# Save initial state
ref = render(canvas_width, canvas_height, shapes, shape_groups)
pydiffvg.imwrite(ref.cpu(), 'results/gaussian_blur/init.png', gamma=2.2)
target = F.gaussian_filter(ref.cpu().numpy(), [10, 10, 0])
target = th.from_numpy(target).to(ref.device)
pydiffvg.imwrite(target.cpu(),
'results/gaussian_blur/target.png',
gamma=2.2)
# Collect variables to optimize
points_vars = []
width_vars = []
for path in shapes:
path.points.requires_grad = True
points_vars.append(path.points)
path.stroke_width.requires_grad = True
width_vars.append(path.stroke_width)
color_vars = []
for group in shape_groups:
# do not optimize alpha
group.fill_color[..., :3].requires_grad = True
color_vars.append(group.fill_color)
# Optimize
points_optim = th.optim.Adam(points_vars, lr=1.0)
width_optim = th.optim.Adam(width_vars, lr=1.0)
color_optim = th.optim.Adam(color_vars, lr=0.01)
for t in range(20):
print('\niteration:', t)
points_optim.zero_grad()
width_optim.zero_grad()
color_optim.zero_grad()
# Forward pass: render the image.
img = render(canvas_width, canvas_height, shapes, shape_groups)
# Save the intermediate render.
pydiffvg.imwrite(img.cpu(),
'results/gaussian_blur/iter_{}.png'.format(t),
gamma=2.2)
loss = (img - target)[..., :3].pow(2).mean()
print('alpha:', img[..., 3].mean().item())
print('render loss:', loss.item())
# Backpropagate the gradients.
loss.backward()
# Take a gradient descent step.
points_optim.step()
width_optim.step()
color_optim.step()
for group in shape_groups:
group.fill_color.data.clamp_(0.0, 1.0)
# Final render
img = render(canvas_width, canvas_height, shapes, shape_groups)
pydiffvg.imwrite(img.cpu(), 'results/gaussian_blur/final.png', gamma=2.2)
# Convert the intermediate renderings to a video.
from subprocess import call
call([
"ffmpeg", "-framerate", "24", "-i",
"results/gaussian_blur/iter_%d.png", "-vb", "20M",
"results/gaussian_blur/out.mp4"
])
inmat[0:2,:]=(np.random.rand(2,3)-0.5)*2
decomp=OptimizableSvg.TransformTools.decompose(inmat)
outmat=OptimizableSvg.TransformTools.recompose(torch.tensor(decomp[0],dtype=torch.float32),torch.tensor(decomp[1],dtype=torch.float32),torch.tensor(decomp[2],dtype=torch.float32),torch.tensor(decomp[3],dtype=torch.float32)).numpy()
dif=np.linalg.norm(inmat-outmat)
if dif > 1e-3:
print(dif)
print(inmat)
print(outmat)
print(decomp)"""
#infile='../../data/test_data/linear_grad_alpha_aspaths.svg'
#infile='../../data/note_small.svg'
infile = 'linux.svg'
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(infile)
scene_args = pydiffvg.RenderFunction.serialize_scene(\
canvas_width, canvas_height, shapes, shape_groups)
render = pydiffvg.RenderFunction.apply
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
*scene_args)
# The output image is in linear RGB space. Do Gamma correction before saving the image.
pydiffvg.imwrite(img.cpu(), 'test_old.png', gamma=1.0)
#optim=OptimizableSvg('linux.svg',verbose=True)
optim = OptimizableSvg(infile, verbose=True)
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--svg",
default=os.path.join("imgs", "seamcarving",
"hokusai.svg"))
parser.add_argument("--optim_steps", default=10, type=int)
parser.add_argument("--lr", default=1e-1, type=int)
args = parser.parse_args()
name = os.path.splitext(os.path.basename(args.svg))[0]
root = os.path.join("results", "seam_carving", name)
svg_root = os.path.join(root, "svg")
os.makedirs(root, exist_ok=True)
os.makedirs(os.path.join(root, "svg"), exist_ok=True)
pydiffvg.set_use_gpu(False)
# pydiffvg.set_device(th.device('cuda'))
# Load SVG
print("loading svg %s" % args.svg)
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(args.svg)
print("done loading")
max_size = 512
scale_factor = max_size / max(canvas_width, canvas_height)
print("rescaling from %dx%d with scale %f" %
(canvas_width, canvas_height, scale_factor))
canvas_width = int(canvas_width * scale_factor)
canvas_height = int(canvas_height * scale_factor)
print("new shape %dx%d" % (canvas_width, canvas_height))
vector_rescale(shapes, scale_x=scale_factor, scale_y=scale_factor)
# Shrink image by 33 %
# num_seams_to_remove = 2
num_seams_to_remove = canvas_width // 3
new_canvas_width = canvas_width - num_seams_to_remove
scaling = new_canvas_width * 1.0 / canvas_width
# Naive scaling baseline
print("rendering naive rescaling...")
vector_rescale(shapes, scale_x=scaling)
resized = render(new_canvas_width, canvas_height, shapes, shape_groups)
pydiffvg.imwrite(resized.cpu(),
os.path.join(root, 'uniform_scaling.png'),
gamma=2.2)
pydiffvg.save_svg(os.path.join(svg_root, 'uniform_scaling.svg'),
canvas_width,
canvas_height,
shapes,
shape_groups,
use_gamma=False)
vector_rescale(shapes,
scale_x=1.0 / scaling) # bring back original coordinates
print("saved naiving scaling")
# Save initial state
print("rendering initial state...")
im = render(canvas_width, canvas_height, shapes, shape_groups)
pydiffvg.imwrite(im.cpu(), os.path.join(root, 'init.png'), gamma=2.2)
pydiffvg.save_svg(os.path.join(svg_root, 'init.svg'),
canvas_width,
canvas_height,
shapes,
shape_groups,
use_gamma=False)
print("saved initial state")
# Optimize
# color_optim = th.optim.Adam(color_vars, lr=0.01)
retargeted = im[..., :3].cpu().numpy()
previous_width = canvas_width
print("carving seams")
for seam_idx in range(num_seams_to_remove):
print('\nseam', seam_idx + 1, 'of', num_seams_to_remove)
# Remove a seam
retargeted = carve_seam(retargeted)
current_width = canvas_width - seam_idx - 1
scale_factor = current_width * 1.0 / previous_width
previous_width = current_width
padded = np.zeros((canvas_height, canvas_width, 4))
padded[:, :-seam_idx - 1, :3] = retargeted
padded[:, :-seam_idx - 1, -1] = 1.0 # alpha
padded = th.from_numpy(padded).to(im.device)
# Remap points to the smaller canvas and
# collect variables to optimize
points_vars = []
# width_vars = []
mini, maxi = canvas_width, 0
for path in shapes:
path.points.requires_grad = False
x = path.points[..., 0]
y = path.points[..., 1]
# rescale
x = x * scale_factor
# clip to canvas
path.points[..., 0] = th.clamp(x, 0, current_width)
path.points[..., 1] = th.clamp(y, 0, canvas_height)
path.points.requires_grad = True
points_vars.append(path.points)
path.stroke_width.requires_grad = True
# width_vars.append(path.stroke_width)
mini = min(mini, path.points.min().item())
maxi = max(maxi, path.points.max().item())
print("points", mini, maxi, "scale", scale_factor)
# recreate an optimizer so we don't carry over the previous update
# (momentum)?
geom_optim = th.optim.Adam(points_vars, lr=args.lr)
for step in range(args.optim_steps):
geom_optim.zero_grad()
img = render(canvas_width,
canvas_height,
shapes,
shape_groups,
samples=2)
pydiffvg.imwrite(img.cpu(),
os.path.join(
root,
"seam_%03d_iter_%02d.png" % (seam_idx, step)),
gamma=2.2)
# NO alpha
loss = (img - padded)[..., :3].pow(2).mean()
# loss = (img - padded).pow(2).mean()
print('render loss:', loss.item())
# Backpropagate the gradients.
loss.backward()
# Take a gradient descent step.
geom_optim.step()
pydiffvg.save_svg(os.path.join(svg_root, "seam%03d.svg" % seam_idx),
canvas_width - seam_idx,
canvas_height,
shapes,
shape_groups,
use_gamma=False)
for path in shapes:
mini = min(mini, path.points.min().item())
maxi = max(maxi, path.points.max().item())
print("points", mini, maxi)
img = render(canvas_width, canvas_height, shapes, shape_groups)
img = img[:, :-num_seams_to_remove]
pydiffvg.imwrite(img.cpu(), os.path.join(root, 'final.png'), gamma=2.2)
pydiffvg.imwrite(retargeted, os.path.join(root, 'ref.png'), gamma=2.2)
pydiffvg.save_svg(os.path.join(svg_root, 'final.svg'),
canvas_width - num_seams_to_remove + 1,
canvas_height,
shapes,
shape_groups,
use_gamma=False)
# Convert the intermediate renderings to a video.
from subprocess import call
call([
"ffmpeg", "-framerate", "24", "-i",
os.path.join(root, "seam_%03d_iter_00.png"), "-vb", "20M",
os.path.join(root, "out.mp4")
])
def main(args):
# set device -> use cpu now since I haven't solved the nvcc issue
pydiffvg.set_use_gpu(False)
# pydiffvg.set_device(torch.device('cuda:1'))
# use L2 for now
# perception_loss = ttools.modules.LPIPS().to(pydiffvg.get_device())
# generate a texture synthesized
target_img = texture_syn(args.target)
tar_h, tar_w = target_img.shape[1], target_img.shape[0]
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(args.svg_path)
# svgpathtools for checking the bounding box
# paths, _, _ = svg2paths2(args.svg_path)
# print(len(paths))
# xmin, xmax, ymin, ymax = big_bounding_box(paths)
# print(xmin, xmax, ymin, ymax)
# input("check")
print('tar h : %d tar w : %d' % (tar_h, tar_w))
print('canvas h : %d canvas w : %d' % (canvas_height, canvas_width))
scale_ratio = tar_h / canvas_height
print("scale ratio : ", scale_ratio)
# input("check")
for path in shapes:
path.points[..., 0] = path.points[..., 0] * scale_ratio
path.points[..., 1] = path.points[..., 1] * scale_ratio
init_img = render(tar_w, tar_h, shapes, shape_groups)
pydiffvg.imwrite(init_img.cpu(),
'results/texture_synthesis/%d/init.png' % (args.case),
gamma=2.2)
# input("check")
random.seed(1234)
torch.manual_seed(1234)
points_vars = []
for path in shapes:
path.points.requires_grad = True
points_vars.append(path.points)
color_vars = []
for group in shape_groups:
group.fill_color.requires_grad = True
color_vars.append(group.fill_color)
# Optimize
points_optim = torch.optim.Adam(points_vars, lr=1.0)
color_optim = torch.optim.Adam(color_vars, lr=0.01)
target = torch.from_numpy(target_img).to(torch.float32) / 255.0
target = target.pow(2.2)
target = target.to(pydiffvg.get_device())
target = target.unsqueeze(0)
target = target.permute(0, 3, 1, 2) # NHWC -> NCHW
canvas_width, canvas_height = target.shape[3], target.shape[2]
# print('canvas h : %d canvas w : %d' % (canvas_height, canvas_width))
# input("check")
for t in range(args.max_iter):
print('iteration:', t)
points_optim.zero_grad()
color_optim.zero_grad()
cur_img = render(canvas_width, canvas_height, shapes, shape_groups)
pydiffvg.imwrite(cur_img.cpu(),
'results/texture_synthesis/%d/iter_%d.png' %
(args.case, t),
gamma=2.2)
cur_img = cur_img[:, :, :3]
cur_img = cur_img.unsqueeze(0)
cur_img = cur_img.permute(0, 3, 1, 2) # NHWC -> NCHW
# perceptual loss
# loss = perception_loss(cur_img, target)
# l2 loss
loss = (cur_img - target).pow(2).mean()
print('render loss:', loss.item())
loss.backward()
points_optim.step()
color_optim.step()
for group in shape_groups:
group.fill_color.data.clamp_(0.0, 1.0)
# write svg
if t % 10 == 0 or t == args.max_iter - 1:
pydiffvg.save_svg(
'results/texture_synthesis/%d/iter_%d.svg' % (args.case, t),
canvas_width, canvas_height, shapes, shape_groups)
# render final result
final_img = render(tar_h, tar_w, shapes, shape_groups)
pydiffvg.imwrite(final_img.cpu(),
'results/texture_synthesis/%d/final.png' % (args.case),
gamma=2.2)
from subprocess import call
call([
"ffmpeg", "-framerate", "24", "-i",
"results/texture_synthesis/%d/iter_%d.png" % (args.case), "-vb", "20M",
"results/texture_synthesis/%d/out.mp4" % (args.case)
])
# make gif
make_gif("results/texture_synthesis/%d" % (args.case),
"results/texture_synthesis/%d/out.gif" % (args.case),
frame_every_X_steps=1,
repeat_ending=3,
total_iter=args.max_iter)
def main(args):
inceptionv3 = models.inception_v3(pretrained=True,
transform_input=False).cuda()
inceptionv3.eval()
perception_loss = ttools.modules.LPIPS().to(pydiffvg.get_device())
canvas_width, canvas_height, shapes, shape_groups = \
pydiffvg.svg_to_scene(args.svg)
scene_args = pydiffvg.RenderFunction.serialize_scene( \
canvas_width, canvas_height, shapes, shape_groups)
render = pydiffvg.RenderFunction.apply
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None, # bg
*scene_args)
# The output image is in linear RGB space. Do Gamma correction before saving the image.
pydiffvg.imwrite(img.cpu(), 'logs/refine_svg/init.png', gamma=gamma)
pydiffvg.imwrite(img.cpu(), 'logs/refine_svg/init_.png')
points_vars = []
for path in shapes:
path.points.requires_grad = True
points_vars.append(path.points)
# color_vars = {}
# for group in shape_groups:
# group.fill_color.requires_grad = True
# color_vars[group.fill_color.data_ptr()] = group.fill_color
# color_vars = list(color_vars.values())
# Optimize
points_optim = torch.optim.Adam(points_vars, lr=1.0)
# color_optim = torch.optim.Adam(color_vars, lr=0.01)
# Adam iterations.
for t in range(args.num_iter):
print('iteration:', t)
points_optim.zero_grad()
# color_optim.zero_grad()
# Forward pass: render the image.
scene_args = pydiffvg.RenderFunction.serialize_scene( \
canvas_width, canvas_height, shapes, shape_groups)
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None, # bg
*scene_args)
# Compose img with white background
img = img[:, :, 3:4] * img[:, :, :3] + torch.ones(
img.shape[0], img.shape[1], 3,
device=pydiffvg.get_device()) * (1 - img[:, :, 3:4])
# Save the intermediate render.
pydiffvg.imwrite(img.cpu(),
'logs/refine_svg/iter_{}.png'.format(t),
gamma=gamma)
img = img[:, :, :3]
# Convert img from HWC to NCHW
img = img.unsqueeze(0)
img = img.permute(0, 3, 1, 2) # NHWC -> NCHW
output = inceptionv3.forward(img.cuda())
get_class(output)
target = torch.autograd.Variable(torch.LongTensor([291]),
requires_grad=False).cuda()
loss = torch.nn.CrossEntropyLoss()(output, target)
print('render loss:', loss.item())
# Backpropagate the gradients.
loss.backward()
# Take a gradient descent step.
points_optim.step()
# color_optim.step()
# for group in shape_groups:
# group.fill_color.data.clamp_(0.0, 1.0)
if t % 10 == 0 or t == args.num_iter - 1:
pydiffvg.save_svg('logs/refine_svg/iter_{}.svg'.format(t),
canvas_width, canvas_height, shapes,
shape_groups)
# Render the final result.
scene_args = pydiffvg.RenderFunction.serialize_scene( \
canvas_width, canvas_height, shapes, shape_groups)
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None, # bg
*scene_args)
# Save the intermediate render.
pydiffvg.imwrite(img.cpu(),
'logs/refine_svg/final.png'.format(t),
gamma=gamma)
import pydiffvg
import matplotlib.pyplot as plt
canvas_width, canvas_height, shapes, shape_groups = pydiffvg.svg_to_scene(
"data/lion.svg")
scene_args = pydiffvg.RenderFunction.serialize_scene(canvas_width,
canvas_height, shapes,
shape_groups)
render = pydiffvg.RenderFunction.apply
img = render(
canvas_width, # width
canvas_height, # height
2, # num_samples_x
2, # num_samples_y
0, # seed
None, # bg
*scene_args)
plt.imshow(img.detach().cpu())
plt.show()