深度学习 Day 16——利用卷神经网络实现咖啡豆的识别

深度学习 Day 16——利用卷神经网络实现咖啡豆的识别

一、前言

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍦 参考文章：365天深度学习训练营-第7周：咖啡豆识别（训练营内部成员可读）
• 🍖 原作者：K同学啊|接辅导、项目定制

因为种种原因，我已经差不多两个星期没有更新有关深度学习方面的博客了，因为我拿不到我这个性能好的电脑，手上只有一个轻薄本没有深度学习环境也带不动这些程序。

不过现在都解决了，可以接着开始学习了，本期我们承接上文，我们仍然学习的是RNN，本期我们将自己搭建VGG-16网络框架进行操作。

浪费了两个星期的时间，我们也不再废话了直接开始工作。

二、我的环境

• 电脑系统：Windows 11
• 语言环境：Python 3.8.5
• 编译器：DataSpell 2022.2
• 深度学习环境：TensorFlow 2.3.4
• 显卡及显存：RTX 3070 8G

三、前期工作

1、导入依赖项并设置GPU

导入依赖项：

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

和之前一样，如果你GPU很好就只使用GPU进行训练，如果GPU不行就推荐使用CPU训练加GPU加速。

只使用GPU：

if gpus:gpu0 = gpus[0]                                        #如果有多个GPU，仅使用第0个GPUtf.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")

使用CPU+GPU：

os.environ["CUDA_VISIBLE_DEVICES"] = "-1"

2、导入数据集

data_dir = "E:\Deep_Learning\data\Day16"
data_dir = pathlib.Path(data_dir)

3、查看数据集

查看数据集内有多少张图片：

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

运行的结果是：

图片总数为： 1200

从数据集内返回一张图片查看一下：

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

四、数据预处理

1、加载数据

我们使用image_dataset_from_directory方法将我们本地的数据加载到tf.data.Dataset

中，并设置训练图片模型参数：

batch_size = 32
img_height = 224
img_width = 224

接下来加载数据：

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)

然后我们再利用class_name输出我们本地数据集的标签，标签也就是对应数据所在的文件目录名：

class_names = train_ds.class_names
print(class_names)

['Dark', 'Green', 'Light', 'Medium']

2、检查数据并可视化数据

在可视化数据前，我们来检查一下我们的数据信息是否是正确的：

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

(32, 224, 224, 3)
(32,)

这是一批形状224x224x3的32张图片，我们将数据进行可视化看看：

plt.figure(figsize=(10, 4))  # 图形的宽为10高为5for images, labels in train_ds.take(1):for i in range(10):ax = plt.subplot(2, 5, i + 1)  plt.imshow(images[i].numpy().astype("uint8"))plt.title(class_names[labels[i]])plt.axis("off")

3、配置数据集并进行归一化处理

AUTOTUNE = tf.data.experimental.AUTOTUNEtrain_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

normalization_layer = layers.experimental.preprocessing.Rescaling(1./255)train_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
val_ds   = val_ds.map(lambda x, y: (normalization_layer(x), y))

image_batch, labels_batch = next(iter(val_ds))
first_image = image_batch[0]# 查看归一化后的数据
print(np.min(first_image), np.max(first_image)) 

打印结果是：

0.0 1.0

上面layers.experimental.preprocessing.Rescaling函数原型是：

tf.keras.layers.experimental.preprocessing.Rescaling(scale, offset=0.0, name=None, **kwargs
)

其中参数：

这里设置scale=1./255的作用是要将[0, 255]范围内的输入重新调整为范围[0, 1]内，也就是缩放层将像素标准化为[0,1]，在后面打印的结果也看出来我们成功将像素标准化为[0,1]。

如果我们要将[0, 255]范围内的输入重新调整为范围[-1, 1]内，我们需要使通过设置scale=1./127.5, offset=-1来实现。

五、构建VGG-16网络

官方模型我在上一期博客中就用到过，训练非常的缓慢，不知道你们是不是和我一样的情况，在这里我们今天主要来试试我们自己搭建VGG-16网络。

from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropoutdef VGG16(nb_classes, input_shape):input_tensor = Input(shape=input_shape)# 1st blockx = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv1')(input_tensor)x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv2')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block1_pool')(x)# 2nd blockx = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv1')(x)x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv2')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block2_pool')(x)# 3rd blockx = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv1')(x)x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv2')(x)x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv3')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block3_pool')(x)# 4th blockx = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv1')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv2')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv3')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block4_pool')(x)# 5th blockx = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv1')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv2')(x)x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv3')(x)x = MaxPooling2D((2,2), strides=(2,2), name = 'block5_pool')(x)# full connectionx = Flatten()(x)x = Dense(4096, activation='relu',  name='fc1')(x)x = Dense(4096, activation='relu', name='fc2')(x)output_tensor = Dense(nb_classes, activation='softmax', name='predictions')(x)model = Model(input_tensor, output_tensor)return modelmodel=VGG16(len(class_names), (img_width, img_height, 3))
model.summary()

打印的结果是：

Model: "functional_5"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_3 (InputLayer)         [(None, 224, 224, 3)]     0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 224, 224, 64)      1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 224, 224, 64)      36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, 112, 112, 64)      0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, 112, 112, 128)     73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, 112, 112, 128)     147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, 56, 56, 128)       0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, 56, 56, 256)       295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, 28, 28, 256)       0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, 28, 28, 512)       1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, 14, 14, 512)       0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, 7, 7, 512)         0         
_________________________________________________________________
flatten_2 (Flatten)          (None, 25088)             0         
_________________________________________________________________
fc1 (Dense)                  (None, 4096)              102764544 
_________________________________________________________________
fc2 (Dense)                  (None, 4096)              16781312  
_________________________________________________________________
predictions (Dense)          (None, 4)                 16388     
=================================================================
Total params: 134,276,932
Trainable params: 134,276,932
Non-trainable params: 0
_________________________________________________________________

六、设置动态学习率、损失函数、优化器，指标为准确率

# 设置初始学习率
initial_learning_rate = 1e-4lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate, decay_steps=30,      # 敲黑板！！！这里是指 steps，不是指epochsdecay_rate=0.92,     # lr经过一次衰减就会变成 decay_rate*lrstaircase=True)# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=initial_learning_rate)model.compile(optimizer=opt,loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics=['accuracy'])

七、训练模型

epochs = 20history = model.fit(train_ds,validation_data=val_ds,epochs=epochs
)

Epoch 1/20
30/30 [==============================] - 13s 187ms/step - loss: 1.3438 - accuracy: 0.3208 - val_loss: 0.9648 - val_accuracy: 0.6750
Epoch 2/20......
30/30 [==============================] - 4s 137ms/step - loss: 0.0537 - accuracy: 0.9781 - val_loss: 0.1639 - val_accuracy: 0.9667
Epoch 19/20
30/30 [==============================] - 4s 138ms/step - loss: 0.0580 - accuracy: 0.9781 - val_loss: 0.1093 - val_accuracy: 0.9625
Epoch 20/20
30/30 [==============================] - 4s 136ms/step - loss: 0.0765 - accuracy: 0.9740 - val_loss: 0.1346 - val_accuracy: 0.9667

八、可视化结果

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()

九、最后我想说

本次项目的结果我并没有运行出来，上面的结果是截取K老师的博客，供大家参考一下。

我也借这次博客来记录一下这个目前无法解决的问题，我自己的结果如下：

这个图跟K老师的完全不一样，代码跟K老师的一样，然后我还在本地跑了一遍K老师项目源码，源码都跑不动，跟K老师讨论了一会，K老师说他之前也遇见过类似的情况，那是3080显卡刚出来的时候，配置的环境没有错，代码也没错但是就是运行结果异常低下，他当时重装了系统解决了问题，我也不知道我的是不是重装系统也能结果，我觉得也有可是跟显卡驱动更新有关，总之这个层面的问题很麻烦，最近快要考试了加上事挺多的，就暂时不去折腾了，如果你们也遇见过类似的问题，可以说说你们的解决办法，谢谢！