- 🍨 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 | 接辅导、项目定制
要求：
- 学习如何编写一个完整的深度学习程序
- 了解分类彩色图片和灰度图片有什么区别
- 测试集accuracy达到72%
我的环境：
- 语言环境：Python 3.8.10
- 编译器：JupyterLab
- 深度学习框架：TensorFlow 2.13.1
- 显卡(GPU)：NVIDIA GeForce RTX 3080 Ti
一、前期工作
1.设置GPU
如果使用的是CPU可以忽略这步。
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
gpu0 = gpus[0] # 如果有多个GPU，仅使用第0个GPU
tf.config.experimental.set_memory_growth(gpu0, True) # 设置GPU显存用量按需使用
tf.config.set_visible_devices([gpu0], "GPU")
2.导入数据
import tensorflow as tf
from tensorflow.keras import datasets, layers, models
import matplotlib.pyplot as plt
(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()
3.归一化
# 将像素的值标准化至0到1的区间内。
train_images, test_images = train_images / 255.0, test_images / 255.0
train_images.shape, test_images.shape, train_labels.shape, test_labels.shape
执行结果：
((50000, 32, 32, 3), (10000, 32, 32, 3), (50000, 1), (10000, 1))
4.可视化
class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
plt.figure(figsize=(20,10))
for i in range(20):
plt.subplot(5,10,i+1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(train_images[i], cmap=plt.cm.binary)
plt.xlabel(class_names[train_labels[i][0]])
plt.show()
执行结果：
二、构建CNN网络
平面结构图：
立体结构图：
model = models.Sequential([
layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)), #卷积层1，卷积核3*3
layers.MaxPooling2D((2, 2)), #池化层1，2*2采样
layers.Conv2D(64, (3, 3), activation='relu'), #卷积层2，卷积核3*3
layers.MaxPooling2D((2, 2)), #池化层2，2*2采样
layers.Conv2D(64, (3, 3), activation='relu'), #卷积层3，卷积核3*3
layers.Flatten(), #Flatten层，连接卷积层与全连接层
layers.Dense(64, activation='relu'), #全连接层，特征进一步提取
layers.Dense(10) #输出层，输出预期结果
])
model.summary() # 打印网络结构
执行结果：
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 30, 30, 32) 896
max_pooling2d (MaxPooling2 (None, 15, 15, 32) 0
D)
conv2d_1 (Conv2D) (None, 13, 13, 64) 18496
max_pooling2d_1 (MaxPoolin (None, 6, 6, 64) 0
g2D)
conv2d_2 (Conv2D) (None, 4, 4, 64) 36928
flatten (Flatten) (None, 1024) 0
dense (Dense) (None, 64) 65600
dense_1 (Dense) (None, 10) 650
=================================================================
Total params: 122570 (478.79 KB)
Trainable params: 122570 (478.79 KB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________
三、编译
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
四、训练模型
history = model.fit(train_images, train_labels, epochs=10,
validation_data=(test_images, test_labels))
执行结果：
Epoch 1/10
1563/1563 [==============================] - 13s 7ms/step - loss: 1.5189 - accuracy: 0.4456 - val_loss: 1.2919 - val_accuracy: 0.5370
Epoch 2/10
1563/1563 [==============================] - 10s 6ms/step - loss: 1.1395 - accuracy: 0.5985 - val_loss: 1.0768 - val_accuracy: 0.6214
Epoch 3/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.9872 - accuracy: 0.6556 - val_loss: 0.9638 - val_accuracy: 0.6660
Epoch 4/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.8951 - accuracy: 0.6873 - val_loss: 0.9616 - val_accuracy: 0.6682
Epoch 5/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.8207 - accuracy: 0.7130 - val_loss: 0.8736 - val_accuracy: 0.7010
Epoch 6/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.7677 - accuracy: 0.7328 - val_loss: 0.8919 - val_accuracy: 0.6953
Epoch 7/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.7189 - accuracy: 0.7470 - val_loss: 0.9046 - val_accuracy: 0.6909
Epoch 8/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.6747 - accuracy: 0.7651 - val_loss: 0.8532 - val_accuracy: 0.7106
Epoch 9/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.6348 - accuracy: 0.7786 - val_loss: 0.8466 - val_accuracy: 0.7182
Epoch 10/10
1563/1563 [==============================] - 10s 6ms/step - loss: 0.5932 - accuracy: 0.7908 - val_loss: 0.8911 - val_accuracy: 0.7154
五、预测
通过模型预测得到的是每一个类别的概率，数字越大该图片的为该类别的可能性就越大。
plt.imshow(test_images[1])
import numpy as np
pre = model.predict(test_images)
print(class_names[np.argmax(pre[1])])
执行结果：
ship
六、模型评估
import matplotlib.pyplot as plt
plt.plot(history.history['accuracy'], label='accuracy')
plt.plot(history.history['val_accuracy'], label='val_accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.ylim([0.5, 1])
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.show()
test_loss, test_accuracy = model.evaluate(test_images, test_labels, verbose=2)
执行结果：
313/313 - 1s - loss: 0.8911 - accuracy: 0.7154
print(test_accuracy)
0.715399980545044
七、模型改进
由于本周打卡其中一个任务是提高测试集accuracy准确率达到72%以上，所以我对优化器进行了一个小小的修改，修改了其中的学习率，同时在CNN网络结构中添加了Dropout层，并且将epochs增加至100。
import matplotlib.pyplot as plt
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=(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')
test_loss, test_accuracy = model.evaluate(test_images, test_labels, verbose=2)
执行结果为：
测试集准确率为：
八、个人总结
本周的深度学习打卡内容是使用TensorFlow框架进行彩色图片分类，首先学习了如何编写一个完整的深度学习程序。本次流程为：设置GPU——导入数据——处理数据——数据可视化——构建简单的CNN网络——编译——训练模型——进行预测——模型评估——模型改进。通过与上周的第T1周：实现mnist手写数字识别对比，在进行归一化时，可知彩色图片分类为RGB三通道，而灰度图片是单通道。最后一个任务是提高测试集的accuracy达到72%以上，自己通过一些尝试（见七、模型改进），将准确率由最初的71.54%提升到了76.55%。
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
