Tensorflow图像分类代码理解

import matplotlib.pyplot as plt
import numpy as np
import os
import PIL   #Python Imaging Library，已经是Python平台事实上的图像处理标准库了
import tensorflow as tf
import matplotlib.pyplot as plt
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
import pathlib
dataset_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz"
data_dir = tf.keras.utils.get_file('flower_photos', origin=dataset_url, untar=True)
data_dir = pathlib.Path(data_dir)

#print(data_dir)

# roses = list(data_dir.glob('roses/*'))
# img1 = PIL.Image.open(str(roses[0]))
#plt.imshow(img1)

#创建数据集
batch_size = 32
img_height = 180
img_width = 180

train_ds = tf.keras.utils.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

class_names = train_ds.class_names
print(class_names)

#可视化数据
plt.figure(figsize=(10, 10))
for images, labels in train_ds.take(1):   #取第一批数据
  for i in range(9):
    ax = plt.subplot(3, 3, i + 1)
    img = images[i].numpy().astype("uint8")
    plt.imshow(img)#plt.imshow()是对图像进行处理
    plt.title(class_names[labels[i]])
    plt.axis("off")
  plt.show()#plt.show（）才是将处理之后的图像显示出来

for image_batch, labels_batch in train_ds:
  print(image_batch.shape)#(32, 180, 180, 3)
  print(labels_batch.shape)#(32,),这些是与32幅图像对应的标签
  break

#为性能配置数据集
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
#数据标准化
normalization_layer = layers.Rescaling(1./255)
normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(normalized_ds))
first_image = image_batch[0]
# Notice the pixel values are now in `[0,1]`.
# print(np.min(first_image), np.max(first_image))

# 创建模型
num_classes = len(class_names)

# model = Sequential([
#   layers.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
#   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(num_classes)
# ])


# # 编译模型
# model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
#               metrics=['accuracy'])
#
# model.summary()
#
# #训练模型
# epochs = 10
# history = model.fit(train_ds, validation_data=val_ds, epochs=epochs
# )

# acc = history.history['accuracy']
# val_acc = history.history['val_accuracy']
#
# loss = history.history['loss']
# val_loss = history.history['val_loss']
#
# epochs_range = range(epochs)
#
# plt.figure(figsize=(8, 8))
# plt.subplot(1, 2, 1)
# plt.plot(epochs_range, acc, label='Training Accuracy')
# plt.plot(epochs_range, val_acc, label='Validation Accuracy')
# plt.legend(loc='lower right')
# plt.title('Training and Validation Accuracy')
#
# plt.subplot(1, 2, 2)
# plt.plot(epochs_range, loss, label='Training Loss')
# plt.plot(epochs_range, val_loss, label='Validation Loss')
# plt.legend(loc='upper right')
# plt.title('Training and Validation Loss')
# plt.show()

#Data augmentation
data_augmentation = keras.Sequential([
    layers.RandomFlip("horizontal", input_shape=(img_height, img_width, 3)),
    layers.RandomRotation(0.1), layers.RandomZoom(0.1),])

# plt.figure(figsize=(10, 10))
# for images, _ in train_ds.take(1):
#   for i in range(9):
#     augmented_images = data_augmentation(images)
#     ax = plt.subplot(3, 3, i + 1)
#     plt.imshow(augmented_images[0].numpy().astype("uint8"))
#     plt.axis("off")
#   plt.show()

#带Dropout的模型
model = Sequential([
  data_augmentation,
  layers.Rescaling(1. / 255),
  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.Dropout(0.2),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])

#Compile and train the model
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

model.summary()

epochs = 15
history = model.fit(train_ds, validation_data=val_ds, epochs=epochs)

#Visualize training results
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

#Predict on new data
sunflower_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/592px-Red_sunflower.jpg"
sunflower_path = tf.keras.utils.get_file('Red_sunflower', origin=sunflower_url)

img = tf.keras.utils.load_img(
    sunflower_path, target_size=(img_height, img_width)
)
img_array = tf.keras.utils.img_to_array(img)# Converts a PIL Image instance to a Numpy array.
img_array = tf.expand_dims(img_array, 0) # Create a batch，在第0维度增加一个长度为1的维度，比如刚开始的img_array是[5,3,1]，扩张1维后变为[1,5,3,1]

predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])

print(
    "This image most likely belongs to {} with a {:.2f} percent confidence."
    .format(class_names[np.argmax(score)], 100 * np.max(score))
)