def optimize(args):
""" Gatys et al. CVPR 2017
ref: Image Style Transfer Using Convolutional Neural Networks
"""
if args.cuda:
ctx = mx.gpu(0)
else:
ctx = mx.cpu(0)
# load the content and style target
content_image = utils.tensor_load_rgbimage(args.content_image,
ctx,
size=args.content_size,
keep_asp=True)
content_image = utils.subtract_imagenet_mean_preprocess_batch(
content_image)
style_image = utils.tensor_load_rgbimage(args.style_image,
ctx,
size=args.style_size)
style_image = utils.subtract_imagenet_mean_preprocess_batch(style_image)
# load the pre-trained vgg-16 and extract features
vgg = net.Vgg16()
utils.init_vgg_params(vgg, 'models', ctx=ctx)
# content feature
f_xc_c = vgg(content_image)[1]
# style feature
features_style = vgg(style_image)
gram_style = [net.gram_matrix(y) for y in features_style]
# output
output = Parameter('output', shape=content_image.shape)
output.initialize(ctx=ctx)
output.set_data(content_image)
# optimizer
trainer = gluon.Trainer([output], 'adam', {'learning_rate': args.lr})
mse_loss = gluon.loss.L2Loss()
# optimizing the images
for e in range(args.iters):
utils.imagenet_clamp_batch(output.data(), 0, 255)
# fix BN for pre-trained vgg
with autograd.record():
features_y = vgg(output.data())
content_loss = 2 * args.content_weight * mse_loss(
features_y[1], f_xc_c)
style_loss = 0.
for m in range(len(features_y)):
gram_y = net.gram_matrix(features_y[m])
gram_s = gram_style[m]
style_loss = style_loss + 2 * args.style_weight * mse_loss(
gram_y, gram_s)
total_loss = content_loss + style_loss
total_loss.backward()
trainer.step(1)
if (e + 1) % args.log_interval == 0:
print('loss:{:.2f}'.format(total_loss.asnumpy()[0]))
# save the image
output = utils.add_imagenet_mean_batch(output.data())
utils.tensor_save_bgrimage(output[0], args.output_image, args.cuda)
def optimize(args):
""" Gatys et al. CVPR 2017
ref: Image Style Transfer Using Convolutional Neural Networks
"""
# load the content and style target
content_image = utils.tensor_load_rgbimage(args.content_image,
size=args.content_size,
keep_asp=True)
content_image = content_image.unsqueeze(0)
content_image = Variable(utils.preprocess_batch(content_image),
requires_grad=False)
content_image = utils.subtract_imagenet_mean_batch(content_image)
style_image = utils.tensor_load_rgbimage(args.style_image,
size=args.style_size)
style_image = style_image.unsqueeze(0)
style_image = Variable(utils.preprocess_batch(style_image),
requires_grad=False)
style_image = utils.subtract_imagenet_mean_batch(style_image)
# load the pre-trained vgg-16 and extract features
vgg = Vgg16()
utils.init_vgg16(args.vgg_model_dir)
vgg.load_state_dict(
torch.load(os.path.join(args.vgg_model_dir, "vgg16.weight")))
if args.cuda:
content_image = content_image.cuda()
style_image = style_image.cuda()
vgg.cuda()
features_content = vgg(content_image)
f_xc_c = Variable(features_content[1].data, requires_grad=False)
features_style = vgg(style_image)
gram_style = [utils.gram_matrix(y) for y in features_style]
# init optimizer
output = Variable(content_image.data, requires_grad=True)
optimizer = Adam([output], lr=args.lr)
mse_loss = torch.nn.MSELoss()
# optimizing the images
for e in range(args.iters):
utils.imagenet_clamp_batch(output, 0, 255)
optimizer.zero_grad()
features_y = vgg(output)
content_loss = args.content_weight * mse_loss(features_y[1], f_xc_c)
style_loss = 0.
for m in range(len(features_y)):
gram_y = utils.gram_matrix(features_y[m])
gram_s = Variable(gram_style[m].data, requires_grad=False)
style_loss += args.style_weight * mse_loss(gram_y, gram_s)
total_loss = content_loss + style_loss
if (e + 1) % args.log_interval == 0:
print(total_loss.data.cpu().numpy()[0])
total_loss.backward()
optimizer.step()
# save the image
output = utils.add_imagenet_mean_batch(output)
utils.tensor_save_bgrimage(output.data[0], args.output_image, args.cuda)
def optimize(args):
""" Gatys et al. CVPR 2017
ref: Image Style Transfer Using Convolutional Neural Networks
"""
if args.cuda:
ctx = mx.gpu(0)
else:
ctx = mx.cpu(0)
# load the content and style target
content_image = utils.tensor_load_rgbimage(args.content_image,ctx, size=args.content_size, keep_asp=True)
content_image = utils.subtract_imagenet_mean_preprocess_batch(content_image)
style_image = utils.tensor_load_rgbimage(args.style_image, ctx, size=args.style_size)
style_image = utils.subtract_imagenet_mean_preprocess_batch(style_image)
# load the pre-trained vgg-16 and extract features
vgg = net.Vgg16()
utils.init_vgg_params(vgg, 'models', ctx=ctx)
# content feature
f_xc_c = vgg(content_image)[1]
# style feature
features_style = vgg(style_image)
gram_style = [net.gram_matrix(y) for y in features_style]
# output
output = Parameter('output', shape=content_image.shape)
output.initialize(ctx=ctx)
output.set_data(content_image)
# optimizer
trainer = gluon.Trainer([output], 'adam',
{'learning_rate': args.lr})
mse_loss = gluon.loss.L2Loss()
# optimizing the images
for e in range(args.iters):
utils.imagenet_clamp_batch(output.data(), 0, 255)
# fix BN for pre-trained vgg
with autograd.record():
features_y = vgg(output.data())
content_loss = 2 * args.content_weight * mse_loss(features_y[1], f_xc_c)
style_loss = 0.
for m in range(len(features_y)):
gram_y = net.gram_matrix(features_y[m])
gram_s = gram_style[m]
style_loss = style_loss + 2 * args.style_weight * mse_loss(gram_y, gram_s)
total_loss = content_loss + style_loss
total_loss.backward()
trainer.step(1)
if (e + 1) % args.log_interval == 0:
print('loss:{:.2f}'.format(total_loss.asnumpy()[0]))
# save the image
output = utils.add_imagenet_mean_batch(output.data())
utils.tensor_save_bgrimage(output[0], args.output_image, args.cuda)
def optimize(args):
content_image = utils.tensor_load_grayimage(args.content_image, size=args.content_size)
content_image = content_image.unsqueeze(0)
content_image = Variable(content_image, requires_grad=False)
content_image = utils.subtract_imagenet_mean_batch_gray(content_image)
style_image = utils.tensor_load_rgbimage(args.style_image, size=args.style_size)
style_image = style_image.unsqueeze(0)
style_image = Variable(utils.preprocess_batch(style_image), requires_grad=False)
style_image = utils.subtract_imagenet_mean_batch(style_image)
# generate the vector field that we want to stylize
# size = args.content_size
# vectors = np.zeros((size, size, 2), dtype=np.float32)
# vortex_spacing = 0.5
# extra_factor = 2.
#
# a = np.array([1, 0]) * vortex_spacing
# b = np.array([np.cos(np.pi / 3), np.sin(np.pi / 3)]) * vortex_spacing
# rnv = int(2 * extra_factor / vortex_spacing)
# vortices = [n * a + m * b for n in range(-rnv, rnv) for m in range(-rnv, rnv)]
# vortices = [(x, y) for (x, y) in vortices if -extra_factor < x < extra_factor and -extra_factor < y < extra_factor]
#
# xs = np.linspace(-1, 1, size).astype(np.float32)[None, :]
# ys = np.linspace(-1, 1, size).astype(np.float32)[:, None]
#
# for (x, y) in vortices:
# rsq = (xs - x) ** 2 + (ys - y) ** 2
# vectors[..., 0] += (ys - y) / rsq
# vectors[..., 1] += -(xs - x) / rsq
#
# for y in range(size):
# for x in range(size):
# angles[y, x] = math.atan(vectors[y, x, 1] / vectors[y, x, 0]) * 180 / math.pi
# for y in range(size):
# for x in range(size):
# xx = float(x - size / 2)
# yy = float(y - size / 2)
# rsq = xx ** 2 + yy ** 2
# if (rsq == 0):
# vectors[y, x, 0] = 0
# vectors[y, x, 1] = 0
# else:
# vectors[y, x, 0] = -yy / rsq
# vectors[y, x, 1] = xx / rsq
# f = h5py.File("../datasets/fake/vector_fields/cat_test3.h5", 'r')
# a_group_key = list(f.keys())[0]
# vectors = f[a_group_key][:]
# vectors = utils.tensor_load_vector_field(vectors)
# vectors = Variable(vectors, requires_grad=False)
# load the pre-trained vgg-16 and extract features
vgg = Vgg16()
# utils.init_vgg16(args.vgg_model_dir)
vgg.load_state_dict(torch.load(os.path.join(args.vgg_model_dir, 'vgg16.weight')))
if args.cuda:
style_image = style_image.cuda()
vgg.cuda()
features_style = vgg(style_image)
gram_style = [utils.gram_matrix(y) for y in features_style]
# load the transformer net and extract features
transformer_phi1 = TransformerNet()
transformer_phi1.load_state_dict(torch.load(args.transformer_model_phi1_path))
if args.cuda:
# vectors = vectors.cuda()
content_image = content_image.cuda()
transformer_phi1.cuda()
vectors = transformer_phi1(content_image)
vectors = Variable(vectors.data, requires_grad=False)
# init optimizer
content_image_size = content_image.data.size()
output_size = np.asarray(content_image_size)
output_size[1] = 3
output_size = torch.Size(output_size)
output = Variable(torch.randn(output_size, device="cuda"), requires_grad=True)
optimizer = Adam([output], lr=args.lr)
mse_loss = torch.nn.MSELoss()
cosine_loss = torch.nn.CosineEmbeddingLoss()
# label = torch.ones(1, 1, args.content_size, args.content_size)
label = torch.ones(1, 128, 128, 128)
if args.cuda:
label = label.cuda()
# optimize the images
transformer_phi2 = TransformerNet()
transformer_phi2.load_state_dict(torch.load(args.transformer_model_phi2_path))
if args.cuda:
transformer_phi2.cuda()
tbar = trange(args.iters)
for e in tbar:
utils.imagenet_clamp_batch(output, 0, 255)
optimizer.zero_grad()
transformer_input = utils.gray_bgr_batch(output)
transformer_y = transformer_phi2(transformer_input)
content_loss = args.content_weight * cosine_loss(vectors, transformer_y, label)
# content_loss = args.content_weight * mse_loss(vectors, transformer_y)
vgg_input = output
features_y = vgg(vgg_input)
style_loss = 0
for m in range(len(features_y)):
gram_y = utils.gram_matrix(features_y[m])
gram_s = Variable(gram_style[m].data, requires_grad=False)
style_loss += args.style_weight * mse_loss(gram_y, gram_s)
total_loss = content_loss + style_loss
# total_loss = content_loss
total_loss.backward()
optimizer.step()
tbar.set_description(str(total_loss.data.cpu().numpy().item()))
if ((e+1) % args.log_interval == 0):
print("iter: %d content_loss: %f style_loss %f" % (e, content_loss.item(), style_loss.item()))
# save the image
output = utils.add_imagenet_mean_batch_device(output, args.cuda)
utils.tensor_save_bgrimage(output.data[0], args.output_image, args.cuda)
def optimize(args):
style_image = utils.tensor_load_rgbimage(args.style_image,
size=args.style_size)
style_image = style_image.unsqueeze(0)
style_image = Variable(utils.preprocess_batch(style_image),
requires_grad=False)
style_image = utils.subtract_imagenet_mean_batch(style_image)
# generate the vector field that we want to backward from
size = args.content_size
vectors = np.zeros((size, size, 2), dtype=np.float32)
vortex_spacing = 0.5
extra_factor = 2.
a = np.array([1, 0]) * vortex_spacing
b = np.array([np.cos(np.pi / 3), np.sin(np.pi / 3)]) * vortex_spacing
rnv = int(2 * extra_factor / vortex_spacing)
vortices = [
n * a + m * b for n in range(-rnv, rnv) for m in range(-rnv, rnv)
]
vortices = [(x, y) for (x, y) in vortices
if -extra_factor < x < extra_factor
and -extra_factor < y < extra_factor]
xs = np.linspace(-1, 1, size).astype(np.float32)[None, :]
ys = np.linspace(-1, 1, size).astype(np.float32)[:, None]
for (x, y) in vortices:
rsq = (xs - x)**2 + (ys - y)**2
vectors[..., 0] += (ys - y) / rsq
vectors[..., 1] += -(xs - x) / rsq
# for y in range(size):
# for x in range(size):
# xx = float(x - size / 2)
# yy = float(y - size / 2)
# rsq = xx ** 2 + yy ** 2
# if rsq == 0:
# vectors[y, x, 0] = 1
# vectors[y, x, 1] = 1
# else:
# vectors[y, x, 0] = -yy / rsq
# vectors[y, x, 1] = xx / rsq
# # vectors[y, x, 0] = 1
# # vectors[y, x, 1] = -1
vectors = utils.tensor_load_vector_field(vectors)
# load the pre-trained vgg-16 and extract features
vgg = Vgg16()
utils.init_vgg16(args.vgg_model_dir)
vgg.load_state_dict(
torch.load(os.path.join(args.vgg_model_dir, 'vgg16.weight')))
if args.cuda:
style_image = style_image.cuda()
vgg.cuda()
features_style = vgg(style_image)
gram_style = [utils.gram_matrix(y) for y in features_style]
# load the sobel network
sobel = Sobel()
if args.cuda:
vectors = vectors.cuda()
sobel.cuda()
# init optimizer
vectors_size = vectors.data.size()
output_size = np.asarray(vectors_size)
output_size[1] = 3
output_size = torch.Size(output_size)
output = Variable(torch.randn(output_size, device="cuda") * 30,
requires_grad=True)
optimizer = Adam([output], lr=args.lr)
cosine_loss = CosineLoss()
mse_loss = torch.nn.MSELoss()
#optimize the images
tbar = trange(args.iters)
for e in tbar:
utils.imagenet_clamp_batch(output, 0, 255)
optimizer.zero_grad()
sobel_input = utils.gray_bgr_batch(output)
sobel_y = sobel(sobel_input)
content_loss = args.content_weight * cosine_loss(vectors, sobel_y)
vgg_input = output
features_y = vgg(vgg_input)
style_loss = 0
for m in range(len(features_y)):
gram_y = utils.gram_matrix(features_y[m])
gram_s = Variable(gram_style[m].data, requires_grad=False)
style_loss += args.style_weight * mse_loss(gram_y, gram_s)
total_loss = content_loss + style_loss
total_loss.backward()
optimizer.step()
if ((e + 1) % args.log_interval == 0):
print("iter: %d content_loss: %f style_loss %f" %
(e, content_loss.item() / args.content_weight,
style_loss.item() / args.style_weight))
tbar.set_description(str(total_loss.data.cpu().numpy().item()))
# save the image
output = utils.add_imagenet_mean_batch_device(output, args.cuda)
utils.tensor_save_bgrimage(output.data[0], args.output_image, args.cuda)
