Script for video face swaping

Script for video face swaping

test_video_swapmutil.py

@@ -0,0 +1,75 @@
+
+import cv2
+import torch
+import fractions
+import numpy as np
+from PIL import Image
+import torch.nn.functional as F
+from torchvision import transforms
+from models.models import create_model
+from options.test_options import TestOptions
+from insightface_func.face_detect_crop_mutil import Face_detect_crop
+from util.videoswap import video_swap
+import os
+from moviepy.editor import AudioFileClip
+
+def lcm(a, b): return abs(a * b) / fractions.gcd(a, b) if a and b else 0
+
+transformer = transforms.Compose([
+        transforms.ToTensor(),
+        #transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    ])
+
+transformer_Arcface = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    ])
+
+detransformer = transforms.Compose([
+        transforms.Normalize([0, 0, 0], [1/0.229, 1/0.224, 1/0.225]),
+        transforms.Normalize([-0.485, -0.456, -0.406], [1, 1, 1])
+    ])
+
+
+if __name__ == '__main__':
+    opt = TestOptions().parse()
+
+    start_epoch, epoch_iter = 1, 0
+    crop_size = 224
+
+    torch.nn.Module.dump_patches = True
+    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))
+
+    pic_a = opt.pic_a_path
+    # img_a = Image.open(pic_a).convert('RGB')
+    img_a_whole = cv2.imread(pic_a)
+    img_a_align_crop, _ = app.get(img_a_whole,crop_size)
+    img_a_align_crop_pil = Image.fromarray(cv2.cvtColor(img_a_align_crop[0],cv2.COLOR_BGR2RGB)) 
+    img_a = transformer_Arcface(img_a_align_crop_pil)
+    img_id = img_a.view(-1, img_a.shape[0], img_a.shape[1], img_a.shape[2])
+
+    # pic_b = opt.pic_b_path
+    # img_b_whole = cv2.imread(pic_b)
+    # img_b_align_crop, b_mat = app.get(img_b_whole,crop_size)
+    # img_b_align_crop_pil = Image.fromarray(cv2.cvtColor(img_b_align_crop,cv2.COLOR_BGR2RGB)) 
+    # img_b = transformer(img_b_align_crop_pil)
+    # img_att = img_b.view(-1, img_b.shape[0], img_b.shape[1], img_b.shape[2])
+
+    # convert numpy to tensor
+    img_id = img_id.cuda()
+    # img_att = img_att.cuda()
+
+    #create latent id
+    img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
+    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)
+    latend_id = latend_id.to('cuda')
+
+    video_swap(opt.video_path, latend_id, model, app, opt.output_path,temp_results_dir=opt.temp_path)
+

test_video_swapsingle.py

@@ -0,0 +1,75 @@
+
+import cv2
+import torch
+import fractions
+import numpy as np
+from PIL import Image
+import torch.nn.functional as F
+from torchvision import transforms
+from models.models import create_model
+from options.test_options import TestOptions
+from insightface_func.face_detect_crop_single import Face_detect_crop
+from util.videoswap import video_swap
+import os
+from moviepy.editor import AudioFileClip
+
+def lcm(a, b): return abs(a * b) / fractions.gcd(a, b) if a and b else 0
+
+transformer = transforms.Compose([
+        transforms.ToTensor(),
+        #transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    ])
+
+transformer_Arcface = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    ])
+
+detransformer = transforms.Compose([
+        transforms.Normalize([0, 0, 0], [1/0.229, 1/0.224, 1/0.225]),
+        transforms.Normalize([-0.485, -0.456, -0.406], [1, 1, 1])
+    ])
+
+
+if __name__ == '__main__':
+    opt = TestOptions().parse()
+
+    start_epoch, epoch_iter = 1, 0
+    crop_size = 224
+
+    torch.nn.Module.dump_patches = True
+    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))
+
+    pic_a = opt.pic_a_path
+    # img_a = Image.open(pic_a).convert('RGB')
+    img_a_whole = cv2.imread(pic_a)
+    img_a_align_crop, _ = app.get(img_a_whole,crop_size)
+    img_a_align_crop_pil = Image.fromarray(cv2.cvtColor(img_a_align_crop[0],cv2.COLOR_BGR2RGB)) 
+    img_a = transformer_Arcface(img_a_align_crop_pil)
+    img_id = img_a.view(-1, img_a.shape[0], img_a.shape[1], img_a.shape[2])
+
+    # pic_b = opt.pic_b_path
+    # img_b_whole = cv2.imread(pic_b)
+    # img_b_align_crop, b_mat = app.get(img_b_whole,crop_size)
+    # img_b_align_crop_pil = Image.fromarray(cv2.cvtColor(img_b_align_crop,cv2.COLOR_BGR2RGB)) 
+    # img_b = transformer(img_b_align_crop_pil)
+    # img_att = img_b.view(-1, img_b.shape[0], img_b.shape[1], img_b.shape[2])
+
+    # convert numpy to tensor
+    img_id = img_id.cuda()
+    # img_att = img_att.cuda()
+
+    #create latent id
+    img_id_downsample = F.interpolate(img_id, scale_factor=0.5)
+    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)
+    latend_id = latend_id.to('cuda')
+
+    video_swap(opt.video_path, latend_id, model, app, opt.output_path,temp_results_dir=opt.temp_path)
+