摘要：我们将给猫贴一张卡通脸，给 Elon Musk 贴上小胡子，给小狗贴上驯鹿角！
本文分享自华为云社区《视频AI，给你的宠物加个表情特效！》，作者：HWCloudAI。
GAN 监督学习是一种联合端到端学习判别模型及其 GAN 生成的训练数据的方法。GANgealing将框架应用于密集视觉对齐问题。受经典 Congealing 方法的启发，GANgealing 算法训练空间变换器将随机样本从在未对齐数据上训练的 GAN 扭曲为共同的、联合学习的目标模式。目标模式已更新，以使空间转换器的工作“尽可能简单”。Spatial Transformer 专门针对 GAN 图像进行训练，并在测试时自动推广到真实图像。
我们可以使用它来进行密集跟踪或创建物镜。例如，我们将给猫贴一张卡通脸，给 Elon Musk 贴上小胡子，给小狗贴上驯鹿角！
安装完成之后需要重启Kernel，重启之后才会加载新安装的PyTorch库
!export CXX=g++ !pip install ninja==1.11.1 ray==2.1.0 plotly==4.14.3 torch==1.10.1 torchvision==0.11.2 moviepy==0.2.3.5 lmdb==0.99
import os import moxing as mox if not os.path.exists('gangealing/'): mox.file.copy_parallel('obs://weilin/gangealing/', 'gangealing/')
cd gangealing/gangealing
model：要检测的物体，celeba 代表人、dog代表狗、 cat代表猫、 cub代表鸟
pic：要添加的特效图片
video_name：要添加特效的视频
model = 'cat' #@param ['celeba', 'dog', 'cat', 'cub'] pic = 'ModelArts.png' video_name = 'demo.mp4' os.environ['RAW_VIDEO_PATH'] = video_name !chmod 777 ./ffmpeg os.environ['FFMPEG_BINARY'] = os.path.join(os.getcwd(), 'ffmpeg')
from pathlib import Path from utils.download import download_model, download_video from applications.mixed_reality import run_gangealing_on_video from applications import load_stn from glob import glob video_resolution = "512" #@param [128, 256, 512, 1024, 2048, 4096, 8192] pad_mode = 'center' #@param ["center", "border"] os.environ['FFMPEG_BINARY'] = os.path.join(os.getcwd(), 'ffmpeg') os.environ['VIDEO_SIZE'] = video_size = str(video_resolution) os.environ['PAD'] = pad_mode video = Path(os.environ['RAW_VIDEO_PATH']).stem os.environ['FRAME_PATH'] = f'data/video_frames/{video}' os.environ['VIDEO_NAME'] = video video_path = f'data/{video}' !chmod 777 process_video.sh !./process_video.sh "$RAW_VIDEO_PATH" !python prepare_data.py --path "$FRAME_PATH" --out "data/$VIDEO_NAME" --pad "$PAD" --size "$VIDEO_SIZE"
根据视频的长度和硬件规格，运行此单元需要几分钟，您可以在下方监控进度。
fps = 30 batch_size = 1 use_flipping = False memory_efficient_but_slower = False if 'cutecat' in video_path: fps = 60 class MyDict(): def __init__(self): pass args = MyDict() args.real_size = int(video_size) args.real_data_path = video_path args.fps = fps args.batch = batch_size args.transform = ['similarity', 'flow'] args.flow_size = 128 args.stn_channel_multiplier = 0.5 args.num_heads = 1 args.distributed = False # Colab only uses 1 GPU args.clustering = False args.cluster = None args.objects = True args.no_flip_inference = not use_flipping args.save_frames = memory_efficient_but_slower args.overlay_congealed = False args.ckpt = model args.override = False args.out = 'visuals' if pic == 'dense tracking': args.label_path = f'assets/masks/{model}_mask.png' # Feel free to change the parameters below: args.resolution = 128 args.sigma = 1.3 args.opacity = 0.8 args.objects = False else: # object lense args.label_path = f'assets/objects/{model}/{pic}' args.resolution = 4 * int(video_size) args.sigma = 0.3 args.opacity = 1.0 args.objects = True stn = load_stn(args) print('Running Spatial Transformer on frames...') run_gangealing_on_video(args, stn, classifier=None) print('Preparing videos to be displayed...') from IPython.display import HTML from base64 import b64encode num = len(list(glob(f'{video}_compressed*'))) compressed_name = f'{video}_compressed{num}.mp4' congealed_compressed_name = f'{video}_compressed_congealed{num}.mp4' path = f'visuals/video_{video}/propagated.mp4' congealed_path = f'visuals/video_{video}/congealed.mp4' os.system(f"ffmpeg -i {path} -vcodec libx264 {compressed_name}") os.system(f"ffmpeg -i {congealed_path} -vcodec libx264 {congealed_compressed_name}")
mp4 = open(video_name,'rb').read() data_url = "data:video/mp4;base64," + b64encode(mp4).decode() HTML("""<video width=512 autoplay controls loop><source src="%s" type="video/mp4"></video>""" % (data_url))
mp4_1 = open(compressed_name,'rb').read() data_url_1 = "data:video/mp4;base64," + b64encode(mp4_1).decode() HTML("""<video width=512 autoplay controls loop><source src="%s" type="video/mp4"></video>""" % (data_url_1))
上传自己的视频，将视频放在gangealing/gangealing/下面
上传自己的图片，将图片放在gangealing/gangealing/assets/objects/*/对应的种类的文件夹下面，自己制作的特效图片尺寸要是8192x8192
修改步骤3里的3个参数，重新运行一遍即可！