在我的理解中，问题在于增强图像仅在模型的一个训练周期中使用一次，甚至没有跨越多个时期。因此，在CPU努力工作的同时，GPU很浪费资源。
我找到了以下解决方案：
- 我尽可能在RAM中生成多个增强图像
- 我使用它们进行训练，跨越几个时期，10到30个时期，直到出现明显的收敛
- 之后，我将生成新批次的增强图像（通过实现on_epoch_end），处理会继续进行。
大部分时间这种方法都能保持GPU繁忙，并且能够从数据增强中获益。我使用自定义Sequence子类来生成增强并同时修复类别不平衡问题。
编辑：添加代码以澄清这个想法
from pyutilz.string import read_config_file
from tqdm.notebook import tqdm
from gc import collect
import numpy as np
import tensorflow
import random
import cv2
class StoppingFromFile(tensorflow.keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs=None):
if read_config_file('control.ini','ML','stop',globals()):
if stop is not None:
if stop==True or stop=='True':
logging.warning(f'Model should be stopped according to the control fole')
self.model.stop_training = True
class AugmentedBalancedSequence(tensorflow.keras.utils.Sequence):
def __init__(self, images_and_classes:dict,input_size:tuple,class_sizes:list, augmentations_fn:object, preprocessing_fn:object, batch_size:int=10,
num_class_samples=100, frame_length:int=5, aug_p:float=0.1,aug_pipe_p:float=0.2,is_validation:bool=False,
disk_saving_prob:float=.01,disk_example_nfiles:int=50):
"""
From a dict of file paths grouped by class label, creates each N epochs augmented balanced training set.
If current class is too scarce, ensures that current frame has no duplicate final images.
If it's rich enough, ensures that current frame has no duplicate base images.
"""
logging.info(f'Got {len(images_and_classes)} classes.')
self.disk_example_nfiles=disk_example_nfiles;self.disk_saving_prob=disk_saving_prob;self.cur_example_file=0
self.images_and_classes=images_and_classes
self.num_class_samples=num_class_samples
self.augmentations_fn=augmentations_fn
self.preprocessing_fn=preprocessing_fn
self.is_validation=is_validation
self.frame_length=frame_length
self.batch_size = batch_size
self.class_sizes=class_sizes
self.input_size=input_size
self.aug_pipe_p=aug_pipe_p
self.aug_p=aug_p
self.images=None
self.epoch = 0
self._generate_data()
def __len__(self):
return int(np.ceil(len(self.images)/ float(self.batch_size)))
def __getitem__(self, idx):
a=idx * self.batch_size;b=a+self.batch_size
return self.images[a:b],self.labels[a:b]
def on_epoch_end(self):
import ast
self.epoch += 1
mydict={}
import pathlib
fname='control.json'
p = pathlib.Path(fname)
if p.is_file():
try:
with open (fname) as f:
mydict=json.load(f)
for var,val in mydict.items():
if hasattr(self,var):
converted = val
if converted is not None:
if getattr(self, var)!=converted:
setattr(self, var, converted)
print(f'{var} became {val}')
except Exception as e:
logging.error(str(e))
if self.epoch % self.frame_length == 0:
self._generate_data()
def _add_sample(self,image,label):
from random import random
idx=self.indices[self.img_sent]
if self.disk_saving_prob>0:
if random()<self.disk_saving_prob:
self.cur_example_file+=1
if self.cur_example_file>self.disk_example_nfiles:
self.cur_example_file=1
Path(r'example_images/').mkdir(parents=True, exist_ok=True)
cv2.imwrite(f'example_images/test{self.cur_example_file}.jpg',cv2.cvtColor(image,cv2.COLOR_RGB2BGR))
if self.preprocessing_fn:
self.images[idx]=self.preprocessing_fn(image)
else:
self.images[idx]=image
self.labels[idx]=label
self.img_sent+=1
def _generate_data(self):
logging.info('Generating new set of augmented data...')
collect()
if self.num_class_samples:
expected_length=len(self.images_and_classes)*self.num_class_samples
else:
expected_length=sum(self.class_sizes.values())
if self.images is None:
self.images=np.empty((expected_length,)+(self.input_size[1],)+(self.input_size[0],)+(3,))
self.labels=np.empty((expected_length),np.int32)
self.indices=np.random.choice(expected_length, expected_length, replace=False)
self.img_sent=0
collect()
relaxed_augmentation_pipeline=self.augmentations_fn(p=self.aug_p,pipe_p=self.aug_pipe_p)
maxed_out_augmentation_pipeline=self.augmentations_fn(p=self.aug_p,pipe_p=1.0)
x,y=[],[]
nartificial=0
for label,images in tqdm(self.images_and_classes.items()):
if self.num_class_samples is None:
for image in images:
self._add_sample(image,label)
else:
if len(images)>=self.num_class_samples:
indices=np.random.choice(len(images), self.num_class_samples, replace=False)
for idx in indices:
if not self.is_validation:
self._add_sample(relaxed_augmentation_pipeline(image=images[idx])['image'],label)
else:
self._add_sample(images[idx],label)
else:
hashes=set()
norig=0
while len(hashes)<self.num_class_samples:
if self.is_validation and norig<len(images):
image=images[norig]
else:
image=maxed_out_augmentation_pipeline(image=random.choice(images))['image']
next_hash=np.sum(image)
if next_hash not in hashes or (self.is_validation and norig<=len(images)):
self._add_sample(image,label)
if next_hash in hashes:
norig+=1
hashes.add(norig)
else:
hashes.add(next_hash)
nartificial+=1
logging.info(f'Generated {self.img_sent} samples ({nartificial} artificial)')
一旦我加载了图片和类，
train_datagen = AugmentedBalancedSequence(images_and_classes=images_and_classes_train,
input_size=INPUT_SIZE,class_sizes=class_sizes_train,num_class_samples=UPSCALE_SAMPLES,
augmentations_fn=get_albumentations_pipeline,aug_p=AUG_P,aug_pipe_p=AUG_PIPE_P,preprocessing_fn=preprocess_input, batch_size=BATCH_SIZE,frame_length=FRAME_LENGTH,disk_saving_prob=0.05)
val_datagen = AugmentedBalancedSequence(images_and_classes=images_and_classes_val,
input_size=INPUT_SIZE,class_sizes=class_sizes_val,num_class_samples=None,
augmentations_fn=get_albumentations_pipeline,preprocessing_fn=preprocess_input, batch_size=BATCH_SIZE,frame_length=FRAME_LENGTH,is_validation=True)
模型实例化后，我执行
model.fit(train_datagen,epochs=600,verbose=1,
validation_data=(val_datagen.images,val_datagen.labels),validation_batch_size=BATCH_SIZE,
callbacks=[checkpointer,StoppingFromFile()],validation_freq=1)
