深度学习之图像分类ResNet50
此次采用迁移学习并微调。一般的建议是:
使用预先训练的模型进行特征提取:使用小型数据集时,通常的做法是利用在相同域中的较大数据集上训练的模型中学习的特征。这是通过实例化预训练的模型并在顶部添加完全连接的分类器来完成的。预先训练的模型是“冻结的”,训练过程中仅更新分类器的权重。在这种情况下,卷积基础提取了与每个图像关联的所有特征,而您刚刚训练了一个分类器,该分类器根据给定的提取特征集确定图像类。
对预训练模型进行微调:为了进一步提高性能,可能需要通过微调将预训练模型的顶层重新用于新的数据集。在这种情况下,您需要调整权重,以使模型学习到特定于数据集的高级功能。通常在训练数据集很大并且与训练前的模型非常相似的原始数据集非常相似时,建议使用此技术。
ResNet50实战
官方示例代码用的二分类,猫狗分类。
另外迁移学习使用的是MobileNet V2 model。
所以这次的更改无非就是更改一下分类层,和引入ResNet即可了。
环境准备
可能有些没有用到!
from tensorflow.keras.applications import ResNet50
from tensorflow.keras import layers
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
from tensorflow.keras import Model
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications.resnet50 import preprocess_input
from tensorflow.keras.preprocessing import image
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras.optimizers import Adam
import tensorflow as tf
import matplotlib.pyplot as plt
import PIL
import numpy as np
数据集
使用的是官方的花朵图像的分类。官方也很无语,图像分类用的是花朵图像,到迁移学习的时候又换成了狗和猫的分类。
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)
拆分数据集
batch_size = 32
img_height = 180
img_width = 180
train_ds = tf.keras.preprocessing.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)
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
查看数据集
plt.figure(figsize=(10, 10))
for images, labels in train_ds.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")
定义model
data_augmentation = tf.keras.Sequential([
tf.keras.layers.experimental.preprocessing.RandomFlip('horizontal'),
tf.keras.layers.experimental.preprocessing.RandomRotation(0.2),
])
for image, _ in train_ds.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')
base_model = ResNet50(include_top=False, weights='imagenet',input_shape=(180,180,3))
base_model.trainable = False
inputs = tf.keras.Input(shape=(180,180,3))
x = data_augmentation(inputs)
x = preprocess_input(x)
x = base_model(x,training=False)
print(base_model.output.shape)
x = GlobalAveragePooling2D()(x)
y = Dense(5, activation='softmax')(x) #final layer with softmax activation
model = Model(inputs=inputs, outputs=y, name="ResNet50")
model.summary()
编译模型
loss = tf.keras.losses.SparseCategoricalCrossentropy()
metrics = tf.metrics.SparseCategoricalAccuracy()
model.compile(optimizer='Adam', loss=loss, metrics=metrics)
len(model.trainable_variables)
训练模型
history = model.fit(train_ds,
epochs=10,
validation_data=val_ds)
基本上就能达到92的准确率。92/92 [==============================] - 19s 206ms/step - loss: 0.0186 - sparse_categorical_accuracy: 1.0000 - val_loss: 0.2470 - val_sparse_categorical_accuracy: 0.9292
微调迁移学习模型
按理说数据量不大,微调可能给不了太大提升。试一下就是了。
175层冻结前面100层
base_model.trainable = True
# Let's take a look to see how many layers are in the base model
print("Number of layers in the base model: ", len(base_model.layers))
# Fine-tune from this layer onwards
fine_tune_at = 100
# Freeze all the layers before the `fine_tune_at` layer
for layer in base_model.layers[:fine_tune_at]:
layer.trainable = False
重新编译模型和训练模型
从未微调的最后一次训练接着训练10个epochs。
loss = tf.keras.losses.SparseCategoricalCrossentropy()
metrics = tf.metrics.SparseCategoricalAccuracy()
model.compile(optimizer='Adam', loss=loss, metrics=metrics)
len(model.trainable_variables)
fine_tune_epochs = 10
total_epochs = 10 + fine_tune_epochs
history_fine = model.fit(train_ds,
epochs=total_epochs,
initial_epoch=history.epoch[-1],
validation_data=val_ds)
结果反而还降低了。92/92 [==============================] - 31s 341ms/step - loss: 0.1780 - sparse_categorical_accuracy: 0.9440 - val_loss: 0.3261 - val_sparse_categorical_accuracy: 0.9183
预测下数据
image_batch,label_batch = val_ds.as_numpy_iterator().next()
print(label_batch)
predictions = model.predict_on_batch(image_batch)
for i in range(0,predictions.shape[0]):
print(np.argmax(predictions[i]))
prediction = np.argmax(predictions[i])
if (prediction != label_batch[i]):
plt.figure(figsize=(10, 10))
plt.imshow(images[i].numpy().astype("uint8"))
plt.title(class_names[label_batch[i]] + "-" + class_names[prediction])
plt.show()
**粗体** _斜体_ [链接](http://example.com) `代码` - 列表 > 引用
。你还可以使用@
来通知其他用户。