CalvinBackup/neuralchen-SimSwap
1
0
Fork 0
Code Issues 288 Pull Requests 16 Actions Packages Projects Releases 2 Wiki Activity

Support Simswap 512

Browse Source 
Support Simswap 512
This commit is contained in:
844294823@qq.com
2021-11-24 19:19:04 +08:00
parent 0f2e4fd244
commit 589e31ad9c
22 changed files with 549 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
MultiSpecific.ipynb
+1 -1
View File
File diff suppressed because one or more lines are too long
SimSwap colab.ipynb
+2 -2
View File
@@ -398,7 +398,7 @@
"opt.isTrain = False\n",
"opt.use_mask = True ## new feature up-to-date\n",
"\n",
"crop_size = 224\n",
"crop_size = opt.crop_size\n",
"\n",
"torch.nn.Module.dump_patches = True\n",
"model = create_model(opt)\n",
@@ -420,7 +420,7 @@
" img_id = img_id.cuda()\n",
"\n",
" #create latent id\n",
" img_id_downsample = F.interpolate(img_id, scale_factor=0.5)\n",
" img_id_downsample = F.interpolate(img_id, size=(112,112))\n",
" latend_id = model.netArc(img_id_downsample)\n",
" latend_id = latend_id.detach().to('cpu')\n",
" latend_id = latend_id/np.linalg.norm(latend_id,axis=1,keepdims=True)\n",
insightface_func/face_detect_crop_multi.py
+12 -3
View File
@@ -1,3 +1,11 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-23 17:03:58
LastEditors: Naiyuan liu
LastEditTime: 2021-11-24 16:45:41
Description:
'''
from __future__ import division
import collections
import numpy as np
@@ -6,7 +14,7 @@ import os
import os.path as osp
import cv2
from insightface.model_zoo import model_zoo
from insightface.utils import face_align
from insightface_func.utils import face_align_ffhqandnewarc as face_align
__all__ = ['Face_detect_crop', 'Face']
@@ -40,8 +48,9 @@ class Face_detect_crop:
self.det_model = self.models['detection']
def prepare(self, ctx_id, det_thresh=0.5, det_size=(640, 640)):
def prepare(self, ctx_id, det_thresh=0.5, det_size=(640, 640), mode ='None'):
self.det_thresh = det_thresh
self.mode = mode
assert det_size is not None
print('set det-size:', det_size)
self.det_size = det_size
@@ -73,7 +82,7 @@ class Face_detect_crop:
kps = None
if kpss is not None:
kps = kpss[i]
M, _ = face_align.estimate_norm(kps, crop_size, mode ='None')
M, _ = face_align.estimate_norm(kps, crop_size, mode = self.mode)
align_img = cv2.warpAffine(img, M, (crop_size, crop_size), borderValue=0.0)
align_img_list.append(align_img)
M_list.append(M)
insightface_func/face_detect_crop_single.py
+12 -3
View File
@@ -1,3 +1,11 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-23 17:03:58
LastEditors: Naiyuan liu
LastEditTime: 2021-11-24 16:46:04
Description:
'''
from __future__ import division
import collections
import numpy as np
@@ -6,7 +14,7 @@ import os
import os.path as osp
import cv2
from insightface.model_zoo import model_zoo
from insightface.utils import face_align
from insightface_func.utils import face_align_ffhqandnewarc as face_align
__all__ = ['Face_detect_crop', 'Face']
@@ -40,8 +48,9 @@ class Face_detect_crop:
self.det_model = self.models['detection']
def prepare(self, ctx_id, det_thresh=0.5, det_size=(640, 640)):
def prepare(self, ctx_id, det_thresh=0.5, det_size=(640, 640), mode ='None'):
self.det_thresh = det_thresh
self.mode = mode
assert det_size is not None
print('set det-size:', det_size)
self.det_size = det_size
@@ -82,7 +91,7 @@ class Face_detect_crop:
kps = None
if kpss is not None:
kps = kpss[best_index]
M, _ = face_align.estimate_norm(kps, crop_size, mode ='None')
M, _ = face_align.estimate_norm(kps, crop_size, mode = self.mode)
align_img = cv2.warpAffine(img, M, (crop_size, crop_size), borderValue=0.0)
return [align_img], [M]
insightface_func/utils/face_align_ffhqandnewarc.py
+159
View File
@@ -0,0 +1,159 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-15 19:42:42
LastEditors: Naiyuan liu
LastEditTime: 2021-11-15 20:01:47
Description:
'''
import cv2
import numpy as np
from skimage import transform as trans
src1 = np.array([[51.642, 50.115], [57.617, 49.990], [35.740, 69.007],
[51.157, 89.050], [57.025, 89.702]],
dtype=np.float32)
#<--left
src2 = np.array([[45.031, 50.118], [65.568, 50.872], [39.677, 68.111],
[45.177, 86.190], [64.246, 86.758]],
dtype=np.float32)
#---frontal
src3 = np.array([[39.730, 51.138], [72.270, 51.138], [56.000, 68.493],
[42.463, 87.010], [69.537, 87.010]],
dtype=np.float32)
#-->right
src4 = np.array([[46.845, 50.872], [67.382, 50.118], [72.737, 68.111],
[48.167, 86.758], [67.236, 86.190]],
dtype=np.float32)
#-->right profile
src5 = np.array([[54.796, 49.990], [60.771, 50.115], [76.673, 69.007],
[55.388, 89.702], [61.257, 89.050]],
dtype=np.float32)
src = np.array([src1, src2, src3, src4, src5])
src_map = src
ffhq_src = np.array([[192.98138, 239.94708], [318.90277, 240.1936], [256.63416, 314.01935],
[201.26117, 371.41043], [313.08905, 371.15118]])
ffhq_src = np.expand_dims(ffhq_src, axis=0)
# arcface_src = np.array(
# [[38.2946, 51.6963], [73.5318, 51.5014], [56.0252, 71.7366],
# [41.5493, 92.3655], [70.7299, 92.2041]],
# dtype=np.float32)
# arcface_src = np.expand_dims(arcface_src, axis=0)
# In[66]:
# lmk is prediction; src is template
def estimate_norm(lmk, image_size=112, mode='ffhq'):
assert lmk.shape == (5, 2)
tform = trans.SimilarityTransform()
lmk_tran = np.insert(lmk, 2, values=np.ones(5), axis=1)
min_M = []
min_index = []
min_error = float('inf')
if mode == 'ffhq':
# assert image_size == 112
src = ffhq_src * image_size / 512
else:
src = src_map * image_size / 112
for i in np.arange(src.shape[0]):
tform.estimate(lmk, src[i])
M = tform.params[0:2, :]
results = np.dot(M, lmk_tran.T)
results = results.T
error = np.sum(np.sqrt(np.sum((results - src[i])**2, axis=1)))
# print(error)
if error < min_error:
min_error = error
min_M = M
min_index = i
return min_M, min_index
def norm_crop(img, landmark, image_size=112, mode='ffhq'):
if mode == 'Both':
M_None, _ = estimate_norm(landmark, image_size, mode = 'newarc')
M_ffhq, _ = estimate_norm(landmark, image_size, mode='ffhq')
warped_None = cv2.warpAffine(img, M_None, (image_size, image_size), borderValue=0.0)
warped_ffhq = cv2.warpAffine(img, M_ffhq, (image_size, image_size), borderValue=0.0)
return warped_ffhq, warped_None
else:
M, pose_index = estimate_norm(landmark, image_size, mode)
warped = cv2.warpAffine(img, M, (image_size, image_size), borderValue=0.0)
return warped
def square_crop(im, S):
if im.shape[0] > im.shape[1]:
height = S
width = int(float(im.shape[1]) / im.shape[0] * S)
scale = float(S) / im.shape[0]
else:
width = S
height = int(float(im.shape[0]) / im.shape[1] * S)
scale = float(S) / im.shape[1]
resized_im = cv2.resize(im, (width, height))
det_im = np.zeros((S, S, 3), dtype=np.uint8)
det_im[:resized_im.shape[0], :resized_im.shape[1], :] = resized_im
return det_im, scale
def transform(data, center, output_size, scale, rotation):
scale_ratio = scale
rot = float(rotation) * np.pi / 180.0
#translation = (output_size/2-center[0]*scale_ratio, output_size/2-center[1]*scale_ratio)
t1 = trans.SimilarityTransform(scale=scale_ratio)
cx = center[0] * scale_ratio
cy = center[1] * scale_ratio
t2 = trans.SimilarityTransform(translation=(-1 * cx, -1 * cy))
t3 = trans.SimilarityTransform(rotation=rot)
t4 = trans.SimilarityTransform(translation=(output_size / 2,
output_size / 2))
t = t1 + t2 + t3 + t4
M = t.params[0:2]
cropped = cv2.warpAffine(data,
M, (output_size, output_size),
borderValue=0.0)
return cropped, M
def trans_points2d(pts, M):
new_pts = np.zeros(shape=pts.shape, dtype=np.float32)
for i in range(pts.shape[0]):
pt = pts[i]
new_pt = np.array([pt[0], pt[1], 1.], dtype=np.float32)
new_pt = np.dot(M, new_pt)
#print('new_pt', new_pt.shape, new_pt)
new_pts[i] = new_pt[0:2]
return new_pts
def trans_points3d(pts, M):
scale = np.sqrt(M[0][0] * M[0][0] + M[0][1] * M[0][1])
#print(scale)
new_pts = np.zeros(shape=pts.shape, dtype=np.float32)
for i in range(pts.shape[0]):
pt = pts[i]
new_pt = np.array([pt[0], pt[1], 1.], dtype=np.float32)
new_pt = np.dot(M, new_pt)
#print('new_pt', new_pt.shape, new_pt)
new_pts[i][0:2] = new_pt[0:2]
new_pts[i][2] = pts[i][2] * scale
return new_pts
def trans_points(pts, M):
if pts.shape[1] == 2:
return trans_points2d(pts, M)
else:
return trans_points3d(pts, M)
models/fs_model.py
+6 -3
View File
@@ -4,10 +4,8 @@ import torch.nn as nn
import torch.nn.functional as F
import os
from torch.autograd import Variable
from util.image_pool import ImagePool
from .base_model import BaseModel
from . import networks
from .fs_networks import Generator_Adain_Upsample, Discriminator
class SpecificNorm(nn.Module):
def __init__(self, epsilon=1e-8):
@@ -52,6 +50,11 @@ class fsModel(BaseModel):
device = torch.device("cuda:0")
if opt.crop_size == 224:
from .fs_networks import Generator_Adain_Upsample, Discriminator
elif opt.crop_size == 512:
from .fs_networks_512 import Generator_Adain_Upsample, Discriminator
# Generator network
self.netG = Generator_Adain_Upsample(input_nc=3, output_nc=3, latent_size=512, n_blocks=9, deep=False)
self.netG.to(device)
@@ -197,7 +200,7 @@ class fsModel(BaseModel):
#G_ID
img_fake_down = F.interpolate(img_fake, scale_factor=0.5)
img_fake_down = F.interpolate(img_fake, size=(112,112))
img_fake_down = self.spNorm(img_fake_down)
latent_fake = self.netArc(img_fake_down)
loss_G_ID = (1 - self.cosin_metric(latent_fake, latent_id))
models/fs_networks_512.py
+232
View File
@@ -0,0 +1,232 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-23 16:55:48
LastEditors: Naiyuan liu
LastEditTime: 2021-11-24 16:58:06
Description:
'''
"""
Copyright (C) 2019 NVIDIA Corporation. All rights reserved.
Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
"""
import torch
import torch.nn as nn
class InstanceNorm(nn.Module):
def __init__(self, epsilon=1e-8):
"""
@notice: avoid in-place ops.
https://discuss.pytorch.org/t/encounter-the-runtimeerror-one-of-the-variables-needed-for-gradient-computation-has-been-modified-by-an-inplace-operation/836/3
"""
super(InstanceNorm, self).__init__()
self.epsilon = epsilon
def forward(self, x):
x = x - torch.mean(x, (2, 3), True)
tmp = torch.mul(x, x) # or x ** 2
tmp = torch.rsqrt(torch.mean(tmp, (2, 3), True) + self.epsilon)
return x * tmp
class ApplyStyle(nn.Module):
"""
@ref: https://github.com/lernapparat/lernapparat/blob/master/style_gan/pytorch_style_gan.ipynb
"""
def __init__(self, latent_size, channels):
super(ApplyStyle, self).__init__()
self.linear = nn.Linear(latent_size, channels * 2)
def forward(self, x, latent):
style = self.linear(latent) # style => [batch_size, n_channels*2]
shape = [-1, 2, x.size(1), 1, 1]
style = style.view(shape) # [batch_size, 2, n_channels, ...]
#x = x * (style[:, 0] + 1.) + style[:, 1]
x = x * (style[:, 0] * 1 + 1.) + style[:, 1] * 1
return x
class ResnetBlock_Adain(nn.Module):
def __init__(self, dim, latent_size, padding_type, activation=nn.ReLU(True)):
super(ResnetBlock_Adain, self).__init__()
p = 0
conv1 = []
if padding_type == 'reflect':
conv1 += [nn.ReflectionPad2d(1)]
elif padding_type == 'replicate':
conv1 += [nn.ReplicationPad2d(1)]
elif padding_type == 'zero':
p = 1
else:
raise NotImplementedError('padding [%s] is not implemented' % padding_type)
conv1 += [nn.Conv2d(dim, dim, kernel_size=3, padding = p), InstanceNorm()]
self.conv1 = nn.Sequential(*conv1)
self.style1 = ApplyStyle(latent_size, dim)
self.act1 = activation
p = 0
conv2 = []
if padding_type == 'reflect':
conv2 += [nn.ReflectionPad2d(1)]
elif padding_type == 'replicate':
conv2 += [nn.ReplicationPad2d(1)]
elif padding_type == 'zero':
p = 1
else:
raise NotImplementedError('padding [%s] is not implemented' % padding_type)
conv2 += [nn.Conv2d(dim, dim, kernel_size=3, padding=p), InstanceNorm()]
self.conv2 = nn.Sequential(*conv2)
self.style2 = ApplyStyle(latent_size, dim)
def forward(self, x, dlatents_in_slice):
y = self.conv1(x)
y = self.style1(y, dlatents_in_slice)
y = self.act1(y)
y = self.conv2(y)
y = self.style2(y, dlatents_in_slice)
out = x + y
return out
class Generator_Adain_Upsample(nn.Module):
def __init__(self, input_nc, output_nc, latent_size, n_blocks=6, deep=False,
norm_layer=nn.BatchNorm2d,
padding_type='reflect'):
assert (n_blocks >= 0)
super(Generator_Adain_Upsample, self).__init__()
activation = nn.ReLU(True)
self.deep = deep
self.first_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(input_nc, 32, kernel_size=7, padding=0),
norm_layer(32), activation)
### downsample
self.down0 = nn.Sequential(nn.Conv2d(32, 64, kernel_size=3, stride=2, padding=1),
norm_layer(64), activation)
self.down1 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1),
norm_layer(128), activation)
self.down2 = nn.Sequential(nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1),
norm_layer(256), activation)
self.down3 = nn.Sequential(nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1),
norm_layer(512), activation)
if self.deep:
self.down4 = nn.Sequential(nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1),
norm_layer(512), activation)
### resnet blocks
BN = []
for i in range(n_blocks):
BN += [
ResnetBlock_Adain(512, latent_size=latent_size, padding_type=padding_type, activation=activation)]
self.BottleNeck = nn.Sequential(*BN)
if self.deep:
self.up4 = nn.Sequential(
nn.Upsample(scale_factor=2, mode='bilinear'),
nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(512), activation
)
self.up3 = nn.Sequential(
nn.Upsample(scale_factor=2, mode='bilinear'),
nn.Conv2d(512, 256, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(256), activation
)
self.up2 = nn.Sequential(
nn.Upsample(scale_factor=2, mode='bilinear'),
nn.Conv2d(256, 128, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(128), activation
)
self.up1 = nn.Sequential(
nn.Upsample(scale_factor=2, mode='bilinear'),
nn.Conv2d(128, 64, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(64), activation
)
self.up0 = nn.Sequential(
nn.Upsample(scale_factor=2, mode='bilinear'),
nn.Conv2d(64, 32, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(32), activation
)
self.last_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(32, output_nc, kernel_size=7, padding=0),
nn.Tanh())
def forward(self, input, dlatents):
x = input # 3*224*224
skip0 = self.first_layer(x)
skip1 = self.down0(skip0)
skip2 = self.down1(skip1)
skip3 = self.down2(skip2)
if self.deep:
skip4 = self.down3(skip3)
x = self.down4(skip4)
else:
x = self.down3(skip3)
for i in range(len(self.BottleNeck)):
x = self.BottleNeck[i](x, dlatents)
if self.deep:
x = self.up4(x)
x = self.up3(x)
x = self.up2(x)
x = self.up1(x)
x = self.up0(x)
x = self.last_layer(x)
x = (x + 1) / 2
return x
class Discriminator(nn.Module):
def __init__(self, input_nc, norm_layer=nn.BatchNorm2d, use_sigmoid=False):
super(Discriminator, self).__init__()
kw = 4
padw = 1
self.down1 = nn.Sequential(
nn.Conv2d(input_nc, 64, kernel_size=kw, stride=2, padding=padw), nn.LeakyReLU(0.2, True)
)
self.down2 = nn.Sequential(
nn.Conv2d(64, 128, kernel_size=kw, stride=2, padding=padw),
norm_layer(128), nn.LeakyReLU(0.2, True)
)
self.down3 = nn.Sequential(
nn.Conv2d(128, 256, kernel_size=kw, stride=2, padding=padw),
norm_layer(256), nn.LeakyReLU(0.2, True)
)
self.down4 = nn.Sequential(
nn.Conv2d(256, 512, kernel_size=kw, stride=2, padding=padw),
norm_layer(512), nn.LeakyReLU(0.2, True)
)
self.conv1 = nn.Sequential(
nn.Conv2d(512, 512, kernel_size=kw, stride=1, padding=padw),
norm_layer(512),
nn.LeakyReLU(0.2, True)
)
if use_sigmoid:
self.conv2 = nn.Sequential(
nn.Conv2d(512, 1, kernel_size=kw, stride=1, padding=padw), nn.Sigmoid()
)
else:
self.conv2 = nn.Sequential(
nn.Conv2d(512, 1, kernel_size=kw, stride=1, padding=padw)
)
def forward(self, input):
out = []
x = self.down1(input)
out.append(x)
x = self.down2(x)
out.append(x)
x = self.down3(x)
out.append(x)
x = self.down4(x)
out.append(x)
x = self.conv1(x)
out.append(x)
x = self.conv2(x)
out.append(x)
return out
options/test_options.py
+9 -1
View File
@@ -1,3 +1,11 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-23 17:03:58
LastEditors: Naiyuan liu
LastEditTime: 2021-11-23 17:08:08
Description:
'''
from .base_options import BaseOptions
class TestOptions(BaseOptions):
@@ -25,6 +33,6 @@ class TestOptions(BaseOptions):
self.parser.add_argument('--id_thres', type=float, default=0.03, help='how many test images to run')
self.parser.add_argument('--no_simswaplogo', action='store_true', help='Remove the watermark')
self.parser.add_argument('--use_mask', action='store_true', help='Use mask for better result')
self.parser.add_argument('--crop_size', type=int, default=224, help='Crop of size of input image')
self.isTrain = False
predict.py
+2 -2
View File
@@ -56,7 +56,7 @@ class Predictor(cog.Predictor):
model = create_model(opt)
model.eval()
crop_size = 224
crop_size = opt.crop_size
spNorm = SpecificNorm()
with torch.no_grad():
@@ -71,7 +71,7 @@ class Predictor(cog.Predictor):
img_id = img_id.cuda()
# create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
test_one_image.py
+1 -1
View File
@@ -53,7 +53,7 @@ if __name__ == '__main__':
img_att = img_att.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = latend_id.detach().to('cpu')
latend_id = latend_id/np.linalg.norm(latend_id,axis=1,keepdims=True)
test_video_swap_multispecific.py
+11 -5
View File
@@ -35,16 +35,22 @@ if __name__ == '__main__':
opt = TestOptions().parse()
pic_specific = opt.pic_specific_path
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
multisepcific_dir = opt.multisepcific_dir
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
model = create_model(opt)
model.eval()
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode=mode)
# The specific person to be swapped(source)
@@ -61,7 +67,7 @@ if __name__ == '__main__':
# convert numpy to tensor
specific_person = specific_person.cuda()
#create latent id
specific_person_downsample = F.interpolate(specific_person, scale_factor=0.5)
specific_person_downsample = F.interpolate(specific_person, size=(112,112))
specific_person_id_nonorm = model.netArc(specific_person_downsample)
source_specific_id_nonorm_list.append(specific_person_id_nonorm.clone())
@@ -80,7 +86,7 @@ if __name__ == '__main__':
# convert numpy to tensor
img_id = img_id.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
target_id_norm_list.append(latend_id.clone())
@@ -90,5 +96,5 @@ if __name__ == '__main__':
video_swap(opt.video_path, target_id_norm_list,source_specific_id_nonorm_list, opt.id_thres, \
model, app, opt.output_path,temp_results_dir=opt.temp_path,no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask)
model, app, opt.output_path,temp_results_dir=opt.temp_path,no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask,crop_size=crop_size)
test_video_swapmulti.py
+19 -5
View File
@@ -1,3 +1,11 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-23 17:03:58
LastEditors: Naiyuan liu
LastEditTime: 2021-11-24 19:00:34
Description:
'''
import cv2
import torch
@@ -34,15 +42,21 @@ if __name__ == '__main__':
opt = TestOptions().parse()
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
model = create_model(opt)
model.eval()
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode = mode)
with torch.no_grad():
pic_a = opt.pic_a_path
@@ -65,10 +79,10 @@ if __name__ == '__main__':
# img_att = img_att.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
video_swap(opt.video_path, latend_id, model, app, opt.output_path,temp_results_dir=opt.temp_path,\
no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask)
no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask,crop_size=crop_size)
test_video_swapsingle.py
+18 -4
View File
@@ -1,3 +1,11 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-23 17:03:58
LastEditors: Naiyuan liu
LastEditTime: 2021-11-24 19:00:38
Description:
'''
import cv2
import torch
@@ -34,15 +42,21 @@ if __name__ == '__main__':
opt = TestOptions().parse()
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
model = create_model(opt)
model.eval()
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode=mode)
with torch.no_grad():
pic_a = opt.pic_a_path
# img_a = Image.open(pic_a).convert('RGB')
@@ -64,10 +78,10 @@ if __name__ == '__main__':
# img_att = img_att.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
video_swap(opt.video_path, latend_id, model, app, opt.output_path,temp_results_dir=opt.temp_path,\
no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask)
no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask,crop_size=crop_size)
test_video_swapspecific.py
+19 -5
View File
@@ -1,3 +1,11 @@
'''
Author: Naiyuan liu
Github: https://github.com/NNNNAI
Date: 2021-11-23 17:03:58
LastEditors: Naiyuan liu
LastEditTime: 2021-11-24 19:00:42
Description:
'''
import cv2
import torch
@@ -34,15 +42,21 @@ if __name__ == '__main__':
opt = TestOptions().parse()
pic_specific = opt.pic_specific_path
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
model = create_model(opt)
model.eval()
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode=mode)
with torch.no_grad():
pic_a = opt.pic_a_path
# img_a = Image.open(pic_a).convert('RGB')
@@ -64,7 +78,7 @@ if __name__ == '__main__':
# img_att = img_att.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
@@ -76,9 +90,9 @@ if __name__ == '__main__':
specific_person = transformer_Arcface(specific_person_align_crop_pil)
specific_person = specific_person.view(-1, specific_person.shape[0], specific_person.shape[1], specific_person.shape[2])
specific_person = specific_person.cuda()
specific_person_downsample = F.interpolate(specific_person, scale_factor=0.5)
specific_person_downsample = F.interpolate(specific_person, size=(112,112))
specific_person_id_nonorm = model.netArc(specific_person_downsample)
video_swap(opt.video_path, latend_id,specific_person_id_nonorm, opt.id_thres, \
model, app, opt.output_path,temp_results_dir=opt.temp_path,no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask)
model, app, opt.output_path,temp_results_dir=opt.temp_path,no_simswaplogo=opt.no_simswaplogo,use_mask=opt.use_mask,crop_size=crop_size)
test_wholeimage_swap_multispecific.py
+13 -5
View File
@@ -38,11 +38,19 @@ if __name__ == '__main__':
opt = TestOptions().parse()
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
multisepcific_dir = opt.multisepcific_dir
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
logoclass = watermark_image('./simswaplogo/simswaplogo.png')
model = create_model(opt)
model.eval()
@@ -52,7 +60,7 @@ if __name__ == '__main__':
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode = mode)
with torch.no_grad():
# The specific person to be swapped(source)
@@ -70,7 +78,7 @@ if __name__ == '__main__':
# convert numpy to tensor
specific_person = specific_person.cuda()
#create latent id
specific_person_downsample = F.interpolate(specific_person, scale_factor=0.5)
specific_person_downsample = F.interpolate(specific_person, size=(112,112))
specific_person_id_nonorm = model.netArc(specific_person_downsample)
source_specific_id_nonorm_list.append(specific_person_id_nonorm.clone())
@@ -89,7 +97,7 @@ if __name__ == '__main__':
# convert numpy to tensor
img_id = img_id.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
target_id_norm_list.append(latend_id.clone())
@@ -112,7 +120,7 @@ if __name__ == '__main__':
b_align_crop_tenor = _totensor(cv2.cvtColor(b_align_crop,cv2.COLOR_BGR2RGB))[None,...].cuda()
b_align_crop_tenor_arcnorm = spNorm(b_align_crop_tenor)
b_align_crop_tenor_arcnorm_downsample = F.interpolate(b_align_crop_tenor_arcnorm, scale_factor=0.5)
b_align_crop_tenor_arcnorm_downsample = F.interpolate(b_align_crop_tenor_arcnorm, size=(112,112))
b_align_crop_id_nonorm = model.netArc(b_align_crop_tenor_arcnorm_downsample)
id_compare_values.append([])
test_wholeimage_swapmulti.py
+9 -3
View File
@@ -31,16 +31,22 @@ if __name__ == '__main__':
opt = TestOptions().parse()
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
logoclass = watermark_image('./simswaplogo/simswaplogo.png')
model = create_model(opt)
model.eval()
spNorm =SpecificNorm()
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode=mode)
with torch.no_grad():
pic_a = opt.pic_a_path
@@ -55,7 +61,7 @@ if __name__ == '__main__':
img_id = img_id.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
test_wholeimage_swapsingle.py
+9 -3
View File
@@ -30,16 +30,22 @@ if __name__ == '__main__':
opt = TestOptions().parse()
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
logoclass = watermark_image('./simswaplogo/simswaplogo.png')
model = create_model(opt)
model.eval()
spNorm =SpecificNorm()
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode=mode)
with torch.no_grad():
pic_a = opt.pic_a_path
@@ -54,7 +60,7 @@ if __name__ == '__main__':
img_id = img_id.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
test_wholeimage_swapspecific.py
+11 -5
View File
@@ -37,9 +37,15 @@ if __name__ == '__main__':
opt = TestOptions().parse()
start_epoch, epoch_iter = 1, 0
crop_size = 224
crop_size = opt.crop_size
torch.nn.Module.dump_patches = True
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
logoclass = watermark_image('./simswaplogo/simswaplogo.png')
model = create_model(opt)
model.eval()
@@ -49,7 +55,7 @@ if __name__ == '__main__':
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640))
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode=mode)
pic_a = opt.pic_a_path
pic_specific = opt.pic_specific_path
@@ -65,7 +71,7 @@ if __name__ == '__main__':
img_id = img_id.cuda()
#create latent id
img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
img_id_downsample = F.interpolate(img_id, size=(112,112))
latend_id = model.netArc(img_id_downsample)
latend_id = F.normalize(latend_id, p=2, dim=1)
@@ -81,7 +87,7 @@ if __name__ == '__main__':
specific_person = specific_person.cuda()
#create latent id
specific_person_downsample = F.interpolate(specific_person, scale_factor=0.5)
specific_person_downsample = F.interpolate(specific_person, size=(112,112))
specific_person_id_nonorm = model.netArc(specific_person_downsample)
# specific_person_id_norm = F.normalize(specific_person_id_nonorm, p=2, dim=1)
@@ -101,7 +107,7 @@ if __name__ == '__main__':
b_align_crop_tenor = _totensor(cv2.cvtColor(b_align_crop,cv2.COLOR_BGR2RGB))[None,...].cuda()
b_align_crop_tenor_arcnorm = spNorm(b_align_crop_tenor)
b_align_crop_tenor_arcnorm_downsample = F.interpolate(b_align_crop_tenor_arcnorm, scale_factor=0.5)
b_align_crop_tenor_arcnorm_downsample = F.interpolate(b_align_crop_tenor_arcnorm, size=(112,112))
b_align_crop_id_nonorm = model.netArc(b_align_crop_tenor_arcnorm_downsample)
id_compare_values.append(mse(b_align_crop_id_nonorm,specific_person_id_nonorm).detach().cpu().numpy())
util/reverse2original.py
+1 -1
View File
@@ -110,7 +110,7 @@ def reverse2wholeimage(b_align_crop_tenor_list,swaped_imgs, mats, crop_size, ori
tgt_mask = encode_segmentation_rgb(vis_parsing_anno)
if tgt_mask.sum() >= 5000:
# face_mask_tensor = tgt_mask[...,0] + tgt_mask[...,1]
target_mask = cv2.resize(tgt_mask, (224, 224))
target_mask = cv2.resize(tgt_mask, (crop_size, crop_size))
# print(source_img)
target_image_parsing = postprocess(swaped_img, source_img[0].cpu().detach().numpy().transpose((1, 2, 0)), target_mask,smooth_mask)
util/videoswap.py
+1
View File
@@ -79,6 +79,7 @@ def video_swap(video_path, id_vetor, swap_model, detect_model, save_path, temp_r
frame_align_crop_tenor = _totensor(cv2.cvtColor(frame_align_crop,cv2.COLOR_BGR2RGB))[None,...].cuda()
swap_result = swap_model(None, frame_align_crop_tenor, id_vetor, None, True)[0]
cv2.imwrite(os.path.join(temp_results_dir, 'frame_{:0>7d}.jpg'.format(frame_index)), frame)
swap_result_list.append(swap_result)
frame_align_crop_tenor_list.append(frame_align_crop_tenor)
util/videoswap_multispecific.py
+1 -1
View File
@@ -83,7 +83,7 @@ def video_swap(video_path, target_id_norm_list,source_specific_id_nonorm_list,id
frame_align_crop_tenor = _totensor(cv2.cvtColor(frame_align_crop,cv2.COLOR_BGR2RGB))[None,...].cuda()
frame_align_crop_tenor_arcnorm = spNorm(frame_align_crop_tenor)
frame_align_crop_tenor_arcnorm_downsample = F.interpolate(frame_align_crop_tenor_arcnorm, scale_factor=0.5)
frame_align_crop_tenor_arcnorm_downsample = F.interpolate(frame_align_crop_tenor_arcnorm, size=(112,112))
frame_align_crop_crop_id_nonorm = swap_model.netArc(frame_align_crop_tenor_arcnorm_downsample)
id_compare_values.append([])
for source_specific_id_nonorm_tmp in source_specific_id_nonorm_list:
util/videoswap_specific.py
+1 -1
View File
@@ -83,7 +83,7 @@ def video_swap(video_path, id_vetor,specific_person_id_nonorm,id_thres, swap_mod
frame_align_crop_tenor = _totensor(cv2.cvtColor(frame_align_crop,cv2.COLOR_BGR2RGB))[None,...].cuda()
frame_align_crop_tenor_arcnorm = spNorm(frame_align_crop_tenor)
frame_align_crop_tenor_arcnorm_downsample = F.interpolate(frame_align_crop_tenor_arcnorm, scale_factor=0.5)
frame_align_crop_tenor_arcnorm_downsample = F.interpolate(frame_align_crop_tenor_arcnorm, size=(112,112))
frame_align_crop_crop_id_nonorm = swap_model.netArc(frame_align_crop_tenor_arcnorm_downsample)
id_compare_values.append(mse(frame_align_crop_crop_id_nonorm,specific_person_id_nonorm).detach().cpu().numpy())