mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-07-06 04:52:13 -07:00
76ca79216e
Removed the wait at first launch for most graphics cards. Increased speed of training by 10-20%, but you have to retrain all models from scratch. SAEHD: added option 'use float16' Experimental option. Reduces the model size by half. Increases the speed of training. Decreases the accuracy of the model. The model may collapse or not train. Model may not learn the mask in large resolutions. true_face_training option is replaced by "True face power". 0.0000 .. 1.0 Experimental option. Discriminates the result face to be more like the src face. Higher value - stronger discrimination. Comparison - https://i.imgur.com/czScS9q.png
81 lines
3 KiB
Python
81 lines
3 KiB
Python
import traceback
|
|
|
|
import cv2
|
|
import numpy as np
|
|
|
|
from core.joblib import SubprocessGenerator, ThisThreadGenerator
|
|
from samplelib import (SampleGeneratorBase, SampleHost, SampleProcessor,
|
|
SampleType)
|
|
|
|
|
|
'''
|
|
output_sample_types = [
|
|
[SampleProcessor.TypeFlags, size, (optional)random_sub_size] ,
|
|
...
|
|
]
|
|
'''
|
|
class SampleGeneratorImageTemporal(SampleGeneratorBase):
|
|
def __init__ (self, samples_path, debug, batch_size, temporal_image_count, sample_process_options=SampleProcessor.Options(), output_sample_types=[], **kwargs):
|
|
super().__init__(samples_path, debug, batch_size)
|
|
|
|
self.temporal_image_count = temporal_image_count
|
|
self.sample_process_options = sample_process_options
|
|
self.output_sample_types = output_sample_types
|
|
|
|
self.samples = SampleHost.load (SampleType.IMAGE, self.samples_path)
|
|
|
|
self.generator_samples = [ self.samples ]
|
|
self.generators = [iter_utils.ThisThreadGenerator ( self.batch_func, 0 )] if self.debug else \
|
|
[iter_utils.SubprocessGenerator ( self.batch_func, 0 )]
|
|
|
|
self.generator_counter = -1
|
|
|
|
def __iter__(self):
|
|
return self
|
|
|
|
def __next__(self):
|
|
self.generator_counter += 1
|
|
generator = self.generators[self.generator_counter % len(self.generators) ]
|
|
return next(generator)
|
|
|
|
def batch_func(self, generator_id):
|
|
samples = self.generator_samples[generator_id]
|
|
samples_len = len(samples)
|
|
if samples_len == 0:
|
|
raise ValueError('No training data provided.')
|
|
|
|
mult_max = 4
|
|
samples_sub_len = samples_len - ( (self.temporal_image_count)*mult_max - (mult_max-1) )
|
|
|
|
if samples_sub_len <= 0:
|
|
raise ValueError('Not enough samples to fit temporal line.')
|
|
|
|
shuffle_idxs = []
|
|
|
|
while True:
|
|
|
|
batches = None
|
|
for n_batch in range(self.batch_size):
|
|
|
|
if len(shuffle_idxs) == 0:
|
|
shuffle_idxs = [ *range(samples_sub_len) ]
|
|
np.random.shuffle (shuffle_idxs)
|
|
|
|
idx = shuffle_idxs.pop()
|
|
|
|
temporal_samples = []
|
|
mult = np.random.randint(mult_max)+1
|
|
for i in range( self.temporal_image_count ):
|
|
sample = samples[ idx+i*mult ]
|
|
try:
|
|
temporal_samples += SampleProcessor.process ([sample], self.sample_process_options, self.output_sample_types, self.debug)[0]
|
|
except:
|
|
raise Exception ("Exception occured in sample %s. Error: %s" % (sample.filename, traceback.format_exc() ) )
|
|
|
|
if batches is None:
|
|
batches = [ [] for _ in range(len(temporal_samples)) ]
|
|
|
|
for i in range(len(temporal_samples)):
|
|
batches[i].append ( temporal_samples[i] )
|
|
|
|
yield [ np.array(batch) for batch in batches]
|