（深度学习记录）第T10周：数据增强

我的环境

• 电脑系统：Windows 11
• 编译器：kaggle在线编译
• 深度学习环境：Tensorflow

代码及结果

import matplotlib.pyplot as plt
import numpy as np
#隐藏警告
import warnings

warnings.filterwarnings('ignore')

from tensorflow.keras import layers
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
    tf.config.experimental.set_memory_growth(gpus[0], True)  
    tf.config.set_visible_devices([gpus[0]],"GPU")

print(gpus)

data_dir   = "/kaggle/input/t10t10"
img_height = 224
img_width  = 224
batch_size = 32
​
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.3,
    subset="training",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.3,
    subset="training",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)

val_batches = tf.data.experimental.cardinality(val_ds)
test_ds     = val_ds.take(val_batches // 5)
val_ds      = val_ds.skip(val_batches // 5)
​
print('Number of validation batches: %d' % tf.data.experimental.cardinality(val_ds))
print('Number of test batches: %d' % tf.data.experimental.cardinality(test_ds))

class_names = train_ds.class_names
print(class_names)

AUTOTUNE = tf.data.AUTOTUNE

def preprocess_image(image,label):
    return (image/255.0,label)

# 归一化处理
train_ds = train_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
val_ds   = val_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
test_ds  = test_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)

train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)
val_ds   = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

plt.figure(figsize=(15, 10))  # 图形的宽为15高为10

for images, labels in train_ds.take(1):
    for i in range(8):
        
        ax = plt.subplot(5, 8, i + 1) 
        plt.imshow(images[i])
        plt.title(class_names[labels[i]])
        
        plt.axis("off")

import tensorflow as tf
from tensorflow.keras.layers.experimental import preprocessing
data_augmentation = tf.keras.Sequential([
  preprocessing.RandomFlip("horizontal_and_vertical"),
  preprocessing.RandomRotation(0.2),
])
image = tf.expand_dims(images[i], 0)
plt.figure(figsize=(8, 8))
for i in range(9):
    augmented_image = data_augmentation(image)
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(augmented_image[0])
    plt.axis("off")

用第一种增强方式

model = tf.keras.Sequential([
  data_augmentation,
  layers.Conv2D(16, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(32, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(64, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(len(class_names))
])
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])
epochs=20
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

loss, acc = model.evaluate(test_ds)
print("Accuracy", acc)

import random
def aug_img(image):
    seed = (random.randint(0,9), 0)
    stateless_random_brightness = tf.image.stateless_random_contrast(image, lower=0.1, upper=1.0, seed=seed)
    return stateless_random_brightness
image = tf.expand_dims(images[3]*255, 0)
print("Min and max pixel values:", image.numpy().min(), image.numpy().max())

plt.figure(figsize=(8, 8))
for i in range(9):
    augmented_image = aug_img(image)
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(augmented_image[0].numpy().astype("uint8"))

    plt.axis("off")

个人总结：

我现在Pycharm上跑的，没有报错，可以运行，后来因为CPU训练太慢，电脑太烫，就转到kaggle上，报了一个错误。

后来代码的第一句先改成了！pip install tensorflow也不好用，最后试了很多，改成了这样

有相同问题的可以试一下