第T7周：咖啡豆识别

• 🍨 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 | 接辅导、项目定制

注：本周由于上周使用VGG-16完成的任务，已经将本周的任务研究的差不多，所以本周只有学习心得。
主要是对学习率的调整，这次数据的数量是1200，比上次少了600.我想着学习率可能会低一些，不过试出来直接跌了一个数量级。最重要的就是掌握了调参的经验。设置学习率尽量少设1开头的，其他数字随便用，一般不会陷入局部最优解，也就是准确率卡在一个地方不动。当准确率出现较大幅度的震荡的时候就是学习率设高了。在峡谷两端跳过去跳过来的。最好的一个设计就是学习率梯度衰减。看我的epoch结果不难看出，在刚开始的时候在准确率有过一次较大幅度的回流，但是后面好多个epoch都只是在升高，这就是学习率梯度下降最香的地方。就像人不能一根筋一样，还是要根据环境改变度量。
还有一个很重要的是，在学习tensorflow的时候，如果没有服务器，在本地跑真的很容易挂内核，建议大家在阿里云或者飞浆或者驱动云申请一些算力，有免费的，需要大家自己去探寻。这种环境跑tensorflow舒服了一亿倍。
不过我还是有不足的地方，就是对于模型参数的计算，中间这个过程参数的变化规律我还是不太会算，准备找个李沐的视频看看，学习一下。不然对轻量化模型没有头绪。

一、前期工作

1.设置GPU

import tensorflow as tf

gpus = tf.config.list_physical_devices("GPU")

if gpus:
    tf.config.experimental.set_memory_growth(gpus[0], True)  #设置GPU显存用量按需使用
    tf.config.set_visible_devices([gpus[0]],"GPU")

2.导入数据

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

data_dir = "./P7/"
data_dir = pathlib.Path(data_dir)

image_count = len(list(data_dir.glob('*/*.png')))

print("图片总数为：",image_count)

输出
图片总数为： 1200

二、数据预处理

1.加载数据

batch_size = 32
img_height = 224
img_width = 224

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)

输出
Found 1200 files belonging to 4 classes.
Using 960 files for training.

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)

输出
Found 1200 files belonging to 4 classes.
Using 240 files for validation.

class_names = train_ds.class_names
print(class_names)

输出
[‘Dark’, ‘Green’, ‘Light’, ‘Medium’]

2.可视化数据

plt.figure(figsize=(10, 4))  

for 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")

输出

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

输出
(32, 224, 224, 3)
(32,)

3.配置数据集

代码知识点
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
这两行代码对训练集和验证集进行了缓存、随机打乱和预取操作。缓存操作将数据集存储在内存中，以便快速访问；随机打乱操作将数据集中的样本随机排列；预取操作则在数据读取时提前加载一部分数据到内存中，以便后续操作能够更快地获取数据。这些操作可以提高数据处理的效率。

AUTOTUNE = tf.data.experimental.AUTOTUNE

train_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]

print(np.min(first_image), np.max(first_image))

输出
0.0 1.0

三、构建VGG-16网络

1. 自建模型

from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout

def VGG16(nb_classes, input_shape):
    input_tensor = Input(shape=input_shape)
    # 1st block
    x = 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 block
    x = 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 block
    x = 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 block
    x = 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 block
    x = 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 connection
    x = 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 model

model=VGG16(len(class_names), (img_width, img_height, 3))
model.summary()

输出

四、编译

# 设置初始学习率
initial_learning_rate = 2e-5

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
        initial_learning_rate, 
        decay_steps=30,     
        decay_rate=0.92,     
        staircase=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'])

五、训练模型

epochs = 20

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

输出

六、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()

输出