DeepFaceLab/merger/FrameInfo.py

from pathlib import Path

class FrameInfo(object):
    def __init__(self, filepath=None, landmarks_list=None):
        self.filepath = filepath
        self.landmarks_list = landmarks_list or []
        self.motion_deg = 0
        self.motion_power = 0
converter: now writes a filename of current frame config, SAE: removed multiscale decoder, because it's not effective 2019-09-13 12:59:00 +08:00			`from pathlib import Path`

Added interactive converter. With interactive converter you can change any parameter of any frame and see the result in real time. Converter: added motion_blur_power param. Motion blur is applied by precomputed motion vectors. So the moving face will look more realistic. RecycleGAN model is removed. Added experimental AVATAR model. Minimum required VRAM is 6GB (NVIDIA), 12GB (AMD) Usage: 1) place data_src.mp4 10-20min square resolution video of news reporter sitting at the table with static background, other faces should not appear in frames. 2) process "extract images from video data_src.bat" with FULL fps 3) place data_dst.mp4 video of face who will control the src face 4) process "extract images from video data_dst FULL FPS.bat" 5) process "data_src mark faces S3FD best GPU.bat" 6) process "data_dst extract unaligned faces S3FD best GPU.bat" 7) train AVATAR.bat stage 1, tune batch size to maximum for your card (32 for 6GB), train to 50k+ iters. 8) train AVATAR.bat stage 2, tune batch size to maximum for your card (4 for 6GB), train to decent sharpness. 9) convert AVATAR.bat 10) converted to mp4.bat updated versions of modules 2019-08-24 16:57:29 +08:00			`class FrameInfo(object):`
1 2020-01-23 02:14:31 +08:00			`def __init__(self, filepath=None, landmarks_list=None):`
			`self.filepath = filepath`
Added interactive converter. With interactive converter you can change any parameter of any frame and see the result in real time. Converter: added motion_blur_power param. Motion blur is applied by precomputed motion vectors. So the moving face will look more realistic. RecycleGAN model is removed. Added experimental AVATAR model. Minimum required VRAM is 6GB (NVIDIA), 12GB (AMD) Usage: 1) place data_src.mp4 10-20min square resolution video of news reporter sitting at the table with static background, other faces should not appear in frames. 2) process "extract images from video data_src.bat" with FULL fps 3) place data_dst.mp4 video of face who will control the src face 4) process "extract images from video data_dst FULL FPS.bat" 5) process "data_src mark faces S3FD best GPU.bat" 6) process "data_dst extract unaligned faces S3FD best GPU.bat" 7) train AVATAR.bat stage 1, tune batch size to maximum for your card (32 for 6GB), train to 50k+ iters. 8) train AVATAR.bat stage 2, tune batch size to maximum for your card (4 for 6GB), train to decent sharpness. 9) convert AVATAR.bat 10) converted to mp4.bat updated versions of modules 2019-08-24 16:57:29 +08:00			`self.landmarks_list = landmarks_list or []`
			`self.motion_deg = 0`
			`self.motion_power = 0`