mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-07-05 20:42:11 -07:00
0c2e1c3944
Maximum resolution is increased to 640. ‘hd’ archi is removed. ‘hd’ was experimental archi created to remove subpixel shake, but ‘lr_dropout’ and ‘disable random warping’ do that better. ‘uhd’ is renamed to ‘-u’ dfuhd and liaeuhd will be automatically renamed to df-u and liae-u in existing models. Added new experimental archi (key -d) which doubles the resolution using the same computation cost. It is mean same configs will be x2 faster, or for example you can set 448 resolution and it will train as 224. Strongly recommended not to train from scratch and use pretrained models. New archi naming: 'df' keeps more identity-preserved face. 'liae' can fix overly different face shapes. '-u' increased likeness of the face. '-d' (experimental) doubling the resolution using the same computation cost Examples: df, liae, df-d, df-ud, liae-ud, ... Improved GAN training (GAN_power option). It was used for dst model, but actually we don’t need it for dst. Instead, a second src GAN model with x2 smaller patch size was added, so the overall quality for hi-res models should be higher. Added option ‘Uniform yaw distribution of samples (y/n)’: Helps to fix blurry side faces due to small amount of them in the faceset. Quick96: Now based on df-ud archi and 20% faster. XSeg trainer: Improved sample generator. Now it randomly adds the background from other samples. Result is reduced chance of random mask noise on the area outside the face. Now you can specify ‘batch_size’ in range 2-16. Reduced size of samples with applied XSeg mask. Thus size of packed samples with applied xseg mask is also reduced.
124 lines
4.5 KiB
Python
124 lines
4.5 KiB
Python
from enum import IntEnum
|
|
from pathlib import Path
|
|
|
|
import cv2
|
|
import numpy as np
|
|
|
|
from core.cv2ex import *
|
|
from facelib import LandmarksProcessor
|
|
from core import imagelib
|
|
from core.imagelib import SegIEPolys
|
|
|
|
class SampleType(IntEnum):
|
|
IMAGE = 0 #raw image
|
|
|
|
FACE_BEGIN = 1
|
|
FACE = 1 #aligned face unsorted
|
|
FACE_PERSON = 2 #aligned face person
|
|
FACE_TEMPORAL_SORTED = 3 #sorted by source filename
|
|
FACE_END = 3
|
|
|
|
QTY = 4
|
|
|
|
class Sample(object):
|
|
__slots__ = ['sample_type',
|
|
'filename',
|
|
'face_type',
|
|
'shape',
|
|
'landmarks',
|
|
'seg_ie_polys',
|
|
'xseg_mask',
|
|
'xseg_mask_compressed',
|
|
'eyebrows_expand_mod',
|
|
'source_filename',
|
|
'person_name',
|
|
'pitch_yaw_roll',
|
|
'_filename_offset_size',
|
|
]
|
|
|
|
def __init__(self, sample_type=None,
|
|
filename=None,
|
|
face_type=None,
|
|
shape=None,
|
|
landmarks=None,
|
|
seg_ie_polys=None,
|
|
xseg_mask=None,
|
|
xseg_mask_compressed=None,
|
|
eyebrows_expand_mod=None,
|
|
source_filename=None,
|
|
person_name=None,
|
|
pitch_yaw_roll=None,
|
|
**kwargs):
|
|
|
|
self.sample_type = sample_type if sample_type is not None else SampleType.IMAGE
|
|
self.filename = filename
|
|
self.face_type = face_type
|
|
self.shape = shape
|
|
self.landmarks = np.array(landmarks) if landmarks is not None else None
|
|
|
|
if isinstance(seg_ie_polys, SegIEPolys):
|
|
self.seg_ie_polys = seg_ie_polys
|
|
else:
|
|
self.seg_ie_polys = SegIEPolys.load(seg_ie_polys)
|
|
|
|
self.xseg_mask = xseg_mask
|
|
self.xseg_mask_compressed = xseg_mask_compressed
|
|
|
|
if self.xseg_mask_compressed is None and self.xseg_mask is not None:
|
|
xseg_mask = np.clip( imagelib.normalize_channels(xseg_mask, 1)*255, 0, 255 ).astype(np.uint8)
|
|
ret, xseg_mask_compressed = cv2.imencode('.png', xseg_mask)
|
|
if not ret:
|
|
raise Exception("Sample(): unable to generate xseg_mask_compressed")
|
|
self.xseg_mask_compressed = xseg_mask_compressed
|
|
self.xseg_mask = None
|
|
|
|
self.eyebrows_expand_mod = eyebrows_expand_mod if eyebrows_expand_mod is not None else 1.0
|
|
self.source_filename = source_filename
|
|
self.person_name = person_name
|
|
self.pitch_yaw_roll = pitch_yaw_roll
|
|
|
|
self._filename_offset_size = None
|
|
|
|
def get_xseg_mask(self):
|
|
if self.xseg_mask_compressed is not None:
|
|
xseg_mask = cv2.imdecode(self.xseg_mask_compressed, cv2.IMREAD_UNCHANGED)
|
|
if len(xseg_mask.shape) == 2:
|
|
xseg_mask = xseg_mask[...,None]
|
|
return xseg_mask.astype(np.float32) / 255.0
|
|
return self.xseg_mask
|
|
|
|
def get_pitch_yaw_roll(self):
|
|
if self.pitch_yaw_roll is None:
|
|
self.pitch_yaw_roll = LandmarksProcessor.estimate_pitch_yaw_roll(self.landmarks, size=self.shape[1])
|
|
return self.pitch_yaw_roll
|
|
|
|
def set_filename_offset_size(self, filename, offset, size):
|
|
self._filename_offset_size = (filename, offset, size)
|
|
|
|
def read_raw_file(self, filename=None):
|
|
if self._filename_offset_size is not None:
|
|
filename, offset, size = self._filename_offset_size
|
|
with open(filename, "rb") as f:
|
|
f.seek( offset, 0)
|
|
return f.read (size)
|
|
else:
|
|
with open(filename, "rb") as f:
|
|
return f.read()
|
|
|
|
def load_bgr(self):
|
|
img = cv2_imread (self.filename, loader_func=self.read_raw_file).astype(np.float32) / 255.0
|
|
return img
|
|
|
|
def get_config(self):
|
|
return {'sample_type': self.sample_type,
|
|
'filename': self.filename,
|
|
'face_type': self.face_type,
|
|
'shape': self.shape,
|
|
'landmarks': self.landmarks.tolist(),
|
|
'seg_ie_polys': self.seg_ie_polys.dump(),
|
|
'xseg_mask' : self.xseg_mask,
|
|
'xseg_mask_compressed' : self.xseg_mask_compressed,
|
|
'eyebrows_expand_mod': self.eyebrows_expand_mod,
|
|
'source_filename': self.source_filename,
|
|
'person_name': self.person_name
|
|
}
|