深度学习之猫狗识别

闲散的猫狗识别，使用新的版本软件会报各种奇奇怪警告提示，发现是需要构建成dataset，在对应官网上的实例写的很分散，这里只是做下汇合，给一个整体视野。

import matplotlib.pyplot as plt
import tensorflow as tf

BATCH_SIZE = 32
IMG_SIZE = (160, 160)
# 数据集地址：https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip
train_dataset = tf.keras.utils.image_dataset_from_directory("tmp/cats_and_dogs/train", batch_size=BATCH_SIZE,
                                                            image_size=IMG_SIZE, shuffle=True)
validation_dataset = tf.keras.utils.image_dataset_from_directory("tmp/cats_and_dogs/validation", batch_size=BATCH_SIZE,
                                                                 image_size=IMG_SIZE, shuffle=True)

class_names = train_dataset.class_names
print("类型：", class_names)

# plt.figure(figsize=(10, 10))
# for images, labels in train_dataset.take(1):
#     for i in range(9):
#         ax = plt.subplot(3, 3, i + 1)
#         plt.imshow(images[i].numpy().astype("uint8"))
#         plt.title(class_names[labels[i]])
#         plt.axis("off")
#
# plt.show()

val_batches = tf.data.experimental.cardinality(validation_dataset)
test_dataset = validation_dataset.take(val_batches // 5)
validation_dataset = validation_dataset.skip(val_batches // 5)

print('Number of validation batches: %d' % tf.data.experimental.cardinality(validation_dataset))
print('Number of test batches: %d' % tf.data.experimental.cardinality(test_dataset))

AUTOTUNE = tf.data.AUTOTUNE

train_dataset = train_dataset.prefetch(buffer_size=AUTOTUNE)
validation_dataset = validation_dataset.prefetch(buffer_size=AUTOTUNE)
test_dataset = test_dataset.prefetch(buffer_size=AUTOTUNE)

IMG_SHAPE = IMG_SIZE + (3,)
base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                               include_top=False,
                                               weights='imagenet')
base_model.trainable = False
model = tf.keras.Sequential([
    tf.keras.Input(shape=(160, 160, 3)),
    tf.keras.layers.RandomFlip('horizontal'),
    tf.keras.layers.RandomRotation(0.2),
    tf.keras.layers.Rescaling(1./127.5, offset=-1),
    base_model,
    tf.keras.layers.GlobalAveragePooling2D(),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Dense(1)
])

# for image, _ in train_dataset.take(1):
#     plt.figure(figsize=(10, 10))
#     first_image = image[0]
#     for i in range(9):
#         ax = plt.subplot(3, 3, i + 1)
#         augmented_image = data_augmentation(tf.expand_dims(first_image, 0))
#         plt.imshow(augmented_image[0] / 255)
#         plt.axis('off')

# Create the base model from the pre-trained model MobileNet V2

# image_batch, label_batch = next(iter(train_dataset))
# feature_batch = base_model(image_batch)
# print(feature_batch.shape)


base_learning_rate = 0.0001
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=base_learning_rate, beta_1=0.9, beta_2=0.999, epsilon=1e-08),
              loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
              metrics=['accuracy'])
initial_epochs = 10
history = model.fit(train_dataset,
                    epochs=initial_epochs,
                    validation_data=validation_dataset)


# Retrieve a batch of images from the test set
image_batch, label_batch = test_dataset.as_numpy_iterator().next()
predictions = model.predict_on_batch(image_batch).flatten()

# Apply a sigmoid since our model returns logits
predictions = tf.nn.sigmoid(predictions)
predictions = tf.where(predictions < 0.5, 0, 1)

print('Predictions:\n', predictions.numpy())
print('Labels:\n', label_batch)

plt.figure(figsize=(10, 10))
for i in range(9):
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(image_batch[i].astype("uint8"))
    plt.title(class_names[predictions[i]])
    plt.axis("off")

plt.show()