T7——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

1.导入及查看数据

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

data_dir='data/咖啡豆数据集-K同学啊'
data_dir=pathlib.Path(data_dir)

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

​

2.加载数据

batch_size=32
img_hight=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)

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)

class_names=train_ds.class_names
print(class_names)

​

3.数据可视化

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")

​

4.检查与配置数据集

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

AUTOTUNE=tf.data.AUTOTUNE
train_ds=train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds=val_ds.cache().prefetch(buffer_size=AUTOTUNE)
#归一化
normalize_layer=layers.experimental.preprocessing.Rescaling(1./255)
train_ds=train_ds.map(lambda x,y:(normalize_layer(x),y))
val_ds=val_ds.map(lambda x,y:(normalize_layer(x),y))

​​

5.构建模型

#调用官方模型
model=tf.keras.applications.VGG16(weights='imagenet')
model.summary()
#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()

​

6.编译及训练模型

initial_learning_rate=1e-4
lr_schedule=tf.keras.optimizers.schedules.ExponentialDecay(
    initial_learning_rate,
    decay_steps=30,
    decay_rate=0.92,
    staircase=True)
opt=tf.keras.optimizers.Adam(learning_rate=initial_learning_rate)
model.compile(optimizer=opt,
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['accuracy'])


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

​

7.结果可视化

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()

​

8.预测数据

model.load_weights('best_model.h5')

from PIL import Image
import numpy as np
img=Image.open("data/48-data/Jennifer Lawrence/003_963a3627.jpg")
image=tf.image.resize(img,[img_hight,img_width])

img_array=tf.expand_dims(image,0)
predictions=model.predict(img_array)
print("预测结果：",class_names[np.argmax(predictions)])

​

总结：

1.VGG-16网络：

VGG优缺点分析：

• VGG优点

VGG的结构非常简洁，整个网络都使用了同样大小的卷积核尺寸（3x3）和最大池化尺寸（2x2）。

• VGG缺点

1)训练时间过长，调参难度大。

2)需要的存储容量大，不利于部署。例如存储VGG-16权重值文件的大小为500多MB，不利于安装到嵌入式系统中。

2.SparseCategoricalCrossentropy函数

from_logits参数：

• 布尔值，默认值为 False。
• 当为 True 时，函数假设传入的预测值是未经过激活函数处理的原始 logits 值。如果模型的最后一层没有使用 softmax 激活函数（即返回 logits），需要将 from_logits 设置为 True。
• 当为 False 时，函数假设传入的预测值已经是经过 softmax 处理的概率分布。