这里有两个用于预处理的函数。第一个将应用于训练和验证数据,以标准化数据并调整网络的预期大小。第二个功能,增强,将仅应用于训练集。您想要执行的增强类型取决于您的数据集和应用程序,但我提供了这个作为示例。
#Fetching, pre-processing & preparing data-pipeline
def preprocess(ds):
x = tf.image.resize_with_pad(ds['image'], IMG_SIZE_W, IMG_SIZE_H)
x = tf.cast(x, tf.float32)
x = (x-MEAN)/(VARIANCE)
y = tf.one_hot(ds['label'], NUM_CLASSES)
return x, y
def augmentation(image,label):
image = tf.image.random_flip_left_right(image)
image = tf.image.resize_with_crop_or_pad(image, IMG_W+4, IMG_W+4) # zero pad each side with 4 pixels
image = tf.image.random_crop(image, size=[BATCH_SIZE, IMG_W, IMG_H, 3]) # Random crop back to 32x32
return image, label
要加载训练和验证数据集,请执行以下操作:
def get_dataset(dataset_name, shuffle_buff_size=1024, batch_size=BATCH_SIZE, augmented=True):
train, info_train = tfds.load(dataset_name, split='train[:80%]', with_info=True)
val, info_val = tfds.load(dataset_name, split='train[80%:]', with_info=True)
TRAIN_SIZE = info_train.splits['train'].num_examples * 0.8
VAL_SIZE = info_train.splits['train'].num_examples * 0.2
train = train.map(preprocess).cache().repeat().shuffle(shuffle_buff_size).batch(batch_size)
if augmented==True:
train = train.map(augmentation)
train = train.prefetch(tf.data.experimental.AUTOTUNE)
val = val.map(preprocess).cache().repeat().batch(batch_size)
val = val.prefetch(tf.data.experimental.AUTOTUNE)
return train, info_train, val, info_val, TRAIN_SIZE, VAL_SIZE