第T3周：天气识别-优快云博客

本文链接：https://blog.youkuaiyun.com/weixin_50792991/article/details/144276173

文为「365天深度学习训练营」内部文章
参考本文所写文章，请在文章开头带上「🔗 声明」

1. 设置GPU

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 os,PIL,pathlib
import matplotlib.pyplot as plt
import numpy             as np
from tensorflow          import keras
from tensorflow.keras    import layers,models

data_dir = r'E:/T3/diwutian/weather_photos'
data_dir = pathlib.Path(data_dir)

3.查看数据

image_count = len(list(data_dir.glob('*/*.jpg')))
print("图片总数为：",image_count)

图片总数为： 1125

roses = list(data_dir.glob('sunrise/*.jpg'))
PIL.Image.open(str(roses[0]))

二.数据预处理

1.加载数据

batch_size = 32
img_height = 180
img_width = 180

"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.youkuaiyun.com/article/details/117018789
"""
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)

Found 1125 files belonging to 4 classes.
Using 900 files for training.

"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.youkuaiyun.com/article/details/117018789
"""
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)

Found 1125 files belonging to 4 classes.
Using 225 files for validation.

class_names = train_ds.class_names
print(class_names)

['cloudy', 'rain', 'shine', 'sunrise']
2.可视化数据

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[labels[i]])
        
        plt.axis("off")

for image_batch, labels_batch in train_ds:
    print(image_batch.shape)
    print(labels_batch.shape)
    break

(32, 180, 180, 3)
(32,)

AUTOTUNE = tf.data.AUTOTUNE

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

num_classes = 4

"""
关于卷积核的计算不懂的可以参考文章：https://blog.youkuaiyun.com/qq_38251616/article/details/114278995

layers.Dropout(0.4) 作用是防止过拟合，提高模型的泛化能力。
在上一篇文章花朵识别中，训练准确率与验证准确率相差巨大就是由于模型过拟合导致的

关于Dropout层的更多介绍可以参考文章：https://mtyjkh.blog.youkuaiyun.com/article/details/115826689
"""

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)), # 卷积层1，卷积核3*3  
    layers.AveragePooling2D((2, 2)),               # 池化层1，2*2采样
    layers.Conv2D(32, (3, 3), activation='relu'),  # 卷积层2，卷积核3*3
    layers.AveragePooling2D((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.Dropout(0.3),                           # 让神经元以一定的概率停止工作，防止过拟合，提高模型的泛化能力。
    
    layers.Flatten(),                       # Flatten层，连接卷积层与全连接层
    layers.Dense(128, activation='relu'),   # 全连接层，特征进一步提取
    layers.Dense(num_classes)               # 输出层，输出预期结果
])

model.summary()  # 打印网络结构

WARNING:tensorflow:From D:\dl\envs\pytorch_gpu\lib\site-packages\keras\src\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 rescaling (Rescaling)       (None, 180, 180, 3)       0         
                                                                 
 conv2d (Conv2D)             (None, 178, 178, 16)      448       
                                                                 
 average_pooling2d (Average  (None, 89, 89, 16)        0         
 Pooling2D)                                                      
                                                                 
 conv2d_1 (Conv2D)           (None, 87, 87, 32)        4640      
                                                                 
 average_pooling2d_1 (Avera  (None, 43, 43, 32)        0         
 gePooling2D)                                                    
                                                                 
 conv2d_2 (Conv2D)           (None, 41, 41, 64)        18496     
                                                                 
 dropout (Dropout)           (None, 41, 41, 64)        0         
                                                                 
 flatten (Flatten)           (None, 107584)            0         
                                                                 
 dense (Dense)               (None, 128)               13770880  
                                                                 
 dense_1 (Dense)             (None, 4)                 516       
                                                                 
=================================================================
Total params: 13794980 (52.62 MB)
Trainable params: 13794980 (52.62 MB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=0.001)

model.compile(optimizer=opt,
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

epochs = 10

history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

Epoch 1/10
WARNING:tensorflow:From D:\dl\envs\pytorch_gpu\lib\site-packages\keras\src\utils\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.

WARNING:tensorflow:From D:\dl\envs\pytorch_gpu\lib\site-packages\keras\src\engine\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.

29/29 [==============================] - 4s 94ms/step - loss: 1.0887 - accuracy: 0.6056 - val_loss: 0.5908 - val_accuracy: 0.7644
Epoch 2/10
29/29 [==============================] - 2s 77ms/step - loss: 0.5110 - accuracy: 0.8111 - val_loss: 0.5650 - val_accuracy: 0.7600
Epoch 3/10
29/29 [==============================] - 2s 75ms/step - loss: 0.4025 - accuracy: 0.8533 - val_loss: 0.5466 - val_accuracy: 0.7867
Epoch 4/10
29/29 [==============================] - 2s 74ms/step - loss: 0.3344 - accuracy: 0.8878 - val_loss: 0.5188 - val_accuracy: 0.8000
Epoch 5/10
29/29 [==============================] - 2s 74ms/step - loss: 0.3307 - accuracy: 0.8811 - val_loss: 0.3947 - val_accuracy: 0.8311
Epoch 6/10
29/29 [==============================] - 2s 75ms/step - loss: 0.2035 - accuracy: 0.9278 - val_loss: 0.5656 - val_accuracy: 0.8444
Epoch 7/10
29/29 [==============================] - 2s 76ms/step - loss: 0.1720 - accuracy: 0.9489 - val_loss: 0.3792 - val_accuracy: 0.8267
Epoch 8/10
29/29 [==============================] - 2s 74ms/step - loss: 0.1591 - accuracy: 0.9456 - val_loss: 0.4851 - val_accuracy: 0.8356
Epoch 9/10
29/29 [==============================] - 2s 75ms/step - loss: 0.1079 - accuracy: 0.9633 - val_loss: 0.6325 - val_accuracy: 0.8044
Epoch 10/10
29/29 [==============================] - 2s 75ms/step - loss: 0.1137 - accuracy: 0.9633 - val_loss: 0.5277 - val_accuracy: 0.8311

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')
plt.show()