??本文 GitHub https://github.com/kzbkzb/Python-AI已收錄
?? 我的環(huán)境：
- 語言環(huán)境：Python3.6.5
- 編譯器：jupyter notebook
- 深度學(xué)習(xí)環(huán)境：TensorFlow2.4.1
- 數(shù)據(jù)和代碼：??【傳送門】
?? 來自專欄：《深度學(xué)習(xí)100例》
如果你是一名深度學(xué)習(xí)小白可以先看看我這個(gè)專門為你寫的專欄：《小白入門深度學(xué)習(xí)》
一、前期工作
1. 設(shè)置GPU
如果使用的是CPU可以忽略這步
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
gpu0 = gpus[0] #如果有多個(gè)GPU，僅使用第0個(gè)GPU
tf.config.experimental.set_memory_growth(gpu0, True) #設(shè)置GPU顯存用量按需使用
tf.config.set_visible_devices([gpu0],"GPU")
2. 導(dǎo)入數(shù)據(jù)
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. 歸一化
# 將像素的值標(biāo)準(zhǔn)化至0到1的區(qū)間內(nèi)。
train_images, test_images = train_images / 255.0, test_images / 255.0
train_images.shape,test_images.shape,train_labels.shape,test_labels.shape
((50000, 32, 32, 3), (10000, 32, 32, 3), (50000, 1), (10000, 1))
4. 可視化
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()
在這里插入圖片描述
二、構(gòu)建CNN網(wǎng)絡(luò)
model = models.Sequential([
layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)), #卷積層1，卷積核3*3
layers.MaxPooling2D((2, 2)), #池化層1，2*2采樣
layers.Conv2D(64, (3, 3), activation='relu'), #卷積層2，卷積核3*3
layers.MaxPooling2D((2, 2)), #池化層2，2*2采樣
layers.Conv2D(64, (3, 3), activation='relu'), #卷積層3，卷積核3*3
layers.Flatten(), #Flatten層，連接卷積層與全連接層
layers.Dense(64, activation='relu'), #全連接層，特征進(jìn)一步提取
layers.Dense(10) #輸出層，輸出預(yù)期結(jié)果
])
model.summary() # 打印網(wǎng)絡(luò)結(jié)構(gòu)
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 30, 30, 32) 896
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 15, 15, 32) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 13, 13, 64) 18496
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 6, 6, 64) 0
_________________________________________________________________
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: 122,570
Trainable params: 122,570
Non-trainable params: 0
_________________________________________________________________
三、編譯
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
四、訓(xùn)練模型
history = model.fit(train_images, train_labels, epochs=10,
validation_data=(test_images, test_labels))
Epoch 1/10
1563/1563 [==============================] - 9s 4ms/step - loss: 1.7862 - accuracy: 0.3390 - val_loss: 1.2697 - val_accuracy: 0.5406
Epoch 2/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.2270 - accuracy: 0.5595 - val_loss: 1.0731 - val_accuracy: 0.6167
Epoch 3/10
1563/1563 [==============================] - 5s 3ms/step - loss: 1.0355 - accuracy: 0.6337 - val_loss: 0.9678 - val_accuracy: 0.6610
Epoch 4/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.9221 - accuracy: 0.6727 - val_loss: 0.9589 - val_accuracy: 0.6648
Epoch 5/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.8474 - accuracy: 0.7022 - val_loss: 0.8962 - val_accuracy: 0.6853
Epoch 6/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.7814 - accuracy: 0.7292 - val_loss: 0.9124 - val_accuracy: 0.6873
Epoch 7/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.7398 - accuracy: 0.7398 - val_loss: 0.8924 - val_accuracy: 0.6929
Epoch 8/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.7008 - accuracy: 0.7542 - val_loss: 0.9809 - val_accuracy: 0.6854
Epoch 9/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.6474 - accuracy: 0.7732 - val_loss: 0.8549 - val_accuracy: 0.7137
Epoch 10/10
1563/1563 [==============================] - 5s 3ms/step - loss: 0.6041 - accuracy: 0.7889 - val_loss: 0.8909 - val_accuracy: 0.7046
五、預(yù)測(cè)
通過模型進(jìn)行預(yù)測(cè)得到的是每一個(gè)類別的概率，數(shù)字越大該圖片為該類別的可能性越大
plt.imshow(test_images[1])
import numpy as np
pre = model.predict(test_images)
print(class_names[np.argmax(pre[1])])
ship
六、模型評(píng)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.show()
test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)
在這里插入圖片描述
313/313 - 0s - loss: 0.8909 - accuracy: 0.7046
print(test_acc)
0.7045999765396118
??本文 GitHub https://github.com/kzbkzb/Python-AI已收錄
