[英]Apply augmentation on tf.data.Dataset.from_generator()
我有这个扩充代码:
class CustomAugment(object):
def __call__(self, sample):
sample = self._random_apply(tf.image.flip_left_right, sample, p=0.5)
sample = self._random_apply(self._color_jitter, sample, p=0.8)
sample = self._random_apply(self._color_drop, sample, p=0.2)
return sample
def _color_jitter(self, x, s=1):
x = tf.image.random_brightness(x, max_delta=0.8*s)
x = tf.image.random_contrast(x, lower=1-0.8*s, upper=1+0.8*s)
x = tf.image.random_saturation(x, lower=1-0.8*s, upper=1+0.8*s)
x = tf.image.random_hue(x, max_delta=0.2*s)
x = tf.clip_by_value(x, 0, 1)
return x
def _color_drop(self, x):
x = tf.image.rgb_to_grayscale(x)
x = tf.tile(x, [1, 1, 1, 3])
return x
def _random_apply(self, func, x, p):
return tf.cond(
tf.less(tf.random.uniform([], minval=0, maxval=1, dtype=tf.float32),
tf.cast(p, tf.float32)),
lambda: func(x),
lambda: x)
这就是我导入图像数据集的方式:
train_ds = tf.data.Dataset.from_generator(path)
我想在我的 train_ds 上应用这种增强功能,请问,我该如何进行?
首先,您应该使用 tf.keras.sequence 的子类创建一个自定义生成器,然后您可以实现__getitem__
和__len__
方法。
class CustomGenerator(tf.keras.utils.Sequence):
def __init__(self, df, X_col, y_col,
batch_size,
input_size=(width, height, channels),
shuffle=True):
self.df = df.copy()
self.X_col = X_col
self.y_col = y_col
self.batch_size = batch_size
self.input_size = input_size
self.n = len(self.df)
self.n_name = df[y_col['label']].nunique()
def on_epoch_end(self):
pass
def __getitem__(self, index):
batches = self.df[index * self.batch_size:(index + 1) *
self.batch_size]
X, y = self.__get_data(batches)
return X, y
def __len__(self):
return self.n // self.batch_size
def __get_output(self, label, num_classes):
return tf.keras.utils.to_categorical(label,
num_classes=num_classes)
def __get_input(self, path, target_size):
# Load Image using PIL
img = Image.open(self.base_path + path)
img = np.array(img)
# Your Augmentation
img = CustomAugment(img)
return img /255
def __get_data(self, batches):
# Generates data containing batch_size samples
img_path_batch = batches[self.X_col['img']]
label_batch = batches[self.y_col['label']]
X_batch = np.asarray([self.__get_input(x, self.input_size)
for x in img_path_batch])
y_batch = np.asarray([self.__get_output(y)
for y in label_batch])
return X_batch, y_batch
如您所见,您将在__get_input
方法中扩充您的样本。
要使用此 class:
traingen = CustomDataGen(df, base_path=IMGS_DIR,
X_col={'img':'img'},
y_col={'label': 'label'},
max_label_len=11,
batch_size=16,
input_size=IMAGE_SIZE)
注意:如果您需要在tf.data
上使用生成器,您应该像这样使用它:
train_dataset = tf.data.Dataset.from_generator(lambda: traingen,
output_types = (tf.float32, tf.int32),
output_shapes = ([None, width, height, channels], [None, num_classes]))
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.