（深度学习记录）第T6周——好莱坞明星识别

•  🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍖 原作者：K同学啊

我的环境

-语言环境：Python3.11

-编译器：PyCharm

-tensorflow版本 2.14.0

代码部分

from tensorflow import keras
from tensorflow.keras import layers,models

import os, PIL, pathlib
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
data_dir = "E:/Administrator/Desktop/biomedical/noml/deeplearning/data/48-data"

data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*.jpg')))

print("图片总数为：",image_count)
roses = list(data_dir.glob('Jennifer Lawrence/*.jpg'))
PIL.Image.open(str(roses[0]))
batch_size = 32
img_height = 214
img_width = 214

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.1,
    subset="training",
    label_mode = "categorical",
    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=0.1,
    subset="validation",
    label_mode = "categorical",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)
class_names = train_ds.class_names
print(class_names)
plt.figure(figsize=(20, 10))

for images, labels in train_ds.take(1):
    for i in range(20):
        ax = plt.subplot(5, 10, i + 1)

        plt.imshow(images[i].numpy().astype("uint8"))
        plt.title(class_names[np.argmax(labels[i])])

        plt.axis("off")
for image_batch, labels_batch in train_ds:
    print(image_batch.shape)
    print(labels_batch.shape)
    break
AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)




model = models.Sequential([
    layers.experimental.preprocessing.Rescaling(1. / 255, input_shape=(img_height, img_width, 3)),

    layers.Conv2D(16, (3, 3), activation='relu', input_shape=(img_height, img_width, 3)),  
    layers.AveragePooling2D((2, 2)),  
    layers.Conv2D(32, (3, 3), activation='relu'), 
    layers.AveragePooling2D((2, 2)), 
    layers.Dropout(0.5),
    layers.Conv2D(64, (3, 3), activation='relu'),  
    layers.AveragePooling2D((2, 2)),
    layers.Dropout(0.5),
    layers.Conv2D(128, (3, 3), activation='relu'),  
    layers.Dropout(0.5),
    layers.Conv2D(64, (3, 3), activation='relu'),  
    layers.AveragePooling2D((2, 2)),
    layers.Dropout(0.5),
    layers.Flatten(),  
    layers.Dense(128, activation='relu'),  
    layers.Dense(len(class_names))  
])

model.summary()  


# 设置初始学习率
# 设置初始学习率
initial_learning_rate = 1e-4

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
        initial_learning_rate,
        decay_steps=60,      
        decay_rate=0.96,     
        staircase=True)

# 将指数衰减学习率送入优化器
optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule)

model.compile(optimizer=optimizer,
              loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])
from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping

epochs = 100

# 保存最佳模型参数
checkpointer = ModelCheckpoint('best_model6.h5',
                                monitor='val_accuracy',
                                verbose=1,
                                save_best_only=True,
                                save_weights_only=True)

# 设置早停
earlystopper = EarlyStopping(monitor='val_accuracy',
                             min_delta=0.001,
                             patience=20,
                             verbose=1)
history = model.fit(train_ds,
                    validation_data=val_ds,
                    epochs=epochs,
                    callbacks=[checkpointer, earlystopper])
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

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

epochs_range = range(len(loss))

plt.figure(figsize=(12, 4))
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()
# 加载效果最好的模型权重
model.load_weights('best_model6.h5')
from PIL import Image
import numpy as np

img = Image.open("E:/Administrator/Desktop/biomedical/noml/deeplearning/data/48-data/Jennifer Lawrence/003_963a3627.jpg") 
image = tf.image.resize(img, [img_height, img_width])

img_array = tf.expand_dims(image, 0)

predictions = model.predict(img_array) 
print("预测结果为：",class_names[np.argmax(predictions)])

结果部分：

个人总结：

自己只是简单的调参了，例如改变训练集验证集的比例，调整图像大小，在增加卷积层和Dropout数增加，但是模型效果都没有很好，甚至更低了，过拟合太严重了。