#第T7周：咖啡豆识别

一、前期工作

1. 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 = "D:/Adashujuxuexi/T7/49-data"
data_dir = pathlib.Path(data_dir)

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

print("图片总数为：",image_count)

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

"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.csdn.net/article/details/117018789
"""
import tensorflow as tf
from tensorflow import keras
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 1200 files belonging to 4 classes.
Using 960 files for training.

"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.csdn.net/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 1200 files belonging to 4 classes.
Using 240 files for validation.

class_names = train_ds.class_names
print(class_names)

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

2. 可视化数据

plt.figure(figsize=(10, 4))  # 图形的宽为10高为5

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")

请添加图片描述

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

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

3. 配置数据集

AUTOTUNE = tf.data.AUTOTUNE

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

# 新版 Keras 写法（无 experimental，直接使用）
normalization_layer = tf.keras.layers.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))

0.0 1.0

三、构建VGG-16网络

1. 官方模型

# model = tf.keras.applications.VGG16(weights='imagenet')
# model.summary()

2. 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()

Model: "functional"

┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ input_layer (InputLayer)             │ (None, 224, 224, 3)         │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block1_conv1 (Conv2D)                │ (None, 224, 224, 64)        │           1,792 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block1_conv2 (Conv2D)                │ (None, 224, 224, 64)        │          36,928 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block1_pool (MaxPooling2D)           │ (None, 112, 112, 64)        │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block2_conv1 (Conv2D)                │ (None, 112, 112, 128)       │          73,856 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block2_conv2 (Conv2D)                │ (None, 112, 112, 128)       │         147,584 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block2_pool (MaxPooling2D)           │ (None, 56, 56, 128)         │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block3_conv1 (Conv2D)                │ (None, 56, 56, 256)         │         295,168 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block3_conv2 (Conv2D)                │ (None, 56, 56, 256)         │         590,080 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block3_conv3 (Conv2D)                │ (None, 56, 56, 256)         │         590,080 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block3_pool (MaxPooling2D)           │ (None, 28, 28, 256)         │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block4_conv1 (Conv2D)                │ (None, 28, 28, 512)         │       1,180,160 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block4_conv2 (Conv2D)                │ (None, 28, 28, 512)         │       2,359,808 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block4_conv3 (Conv2D)                │ (None, 28, 28, 512)         │       2,359,808 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block4_pool (MaxPooling2D)           │ (None, 14, 14, 512)         │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block5_conv1 (Conv2D)                │ (None, 14, 14, 512)         │       2,359,808 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block5_conv2 (Conv2D)                │ (None, 14, 14, 512)         │       2,359,808 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block5_conv3 (Conv2D)                │ (None, 14, 14, 512)         │       2,359,808 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ block5_pool (MaxPooling2D)           │ (None, 7, 7, 512)           │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ flatten (Flatten)                    │ (None, 25088)               │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ fc1 (Dense)                          │ (None, 4096)                │     102,764,544 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ fc2 (Dense)                          │ (None, 4096)                │      16,781,312 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ predictions (Dense)                  │ (None, 4)                   │          16,388 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘

 Total params: 134,276,932 (512.23 MB)

 Trainable params: 134,276,932 (512.23 MB)

 Non-trainable params: 0 (0.00 B)

3. 网络结构图

四、编译

# 设置初始学习率
initial_learning_rate = 1e-4

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
        initial_learning_rate, 
        decay_steps=30,      # 敲黑板！！！这里是指 steps，不是指epochs
        decay_rate=0.92,     # lr经过一次衰减就会变成 decay_rate*lr
        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=False),
              metrics=['accuracy'])

WARNING:tensorflow:TensorFlow GPU support is not available on native Windows for TensorFlow >= 2.11. Even if CUDA/cuDNN are installed, GPU will not be used. Please use WSL2 or the TensorFlow-DirectML plugin.

五、训练模型

epochs = 20

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

Epoch 1/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m217s[0m 7s/step - accuracy: 0.2885 - loss: 1.3947 - val_accuracy: 0.2208 - val_loss: 1.3970
Epoch 2/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m215s[0m 7s/step - accuracy: 0.4396 - loss: 1.2140 - val_accuracy: 0.5417 - val_loss: 1.0674
Epoch 3/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m217s[0m 7s/step - accuracy: 0.5865 - loss: 0.7629 - val_accuracy: 0.7333 - val_loss: 0.5709
Epoch 4/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.6573 - loss: 0.6354 - val_accuracy: 0.6542 - val_loss: 0.6734
Epoch 5/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m213s[0m 7s/step - accuracy: 0.7260 - loss: 0.5551 - val_accuracy: 0.7958 - val_loss: 0.5688
Epoch 6/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m214s[0m 7s/step - accuracy: 0.7417 - loss: 0.4794 - val_accuracy: 0.7917 - val_loss: 0.4392
Epoch 7/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m213s[0m 7s/step - accuracy: 0.8260 - loss: 0.4154 - val_accuracy: 0.7375 - val_loss: 0.7130
Epoch 8/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m215s[0m 7s/step - accuracy: 0.8625 - loss: 0.3472 - val_accuracy: 0.8958 - val_loss: 0.3504
Epoch 9/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m211s[0m 7s/step - accuracy: 0.8844 - loss: 0.2911 - val_accuracy: 0.9500 - val_loss: 0.1357
Epoch 10/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.9552 - loss: 0.1501 - val_accuracy: 0.9333 - val_loss: 0.1780
Epoch 11/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.9604 - loss: 0.0992 - val_accuracy: 0.9458 - val_loss: 0.1354
Epoch 12/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.9729 - loss: 0.0815 - val_accuracy: 0.9500 - val_loss: 0.1555
Epoch 13/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.9667 - loss: 0.0857 - val_accuracy: 0.9667 - val_loss: 0.1422
Epoch 14/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.9688 - loss: 0.1141 - val_accuracy: 0.9333 - val_loss: 0.2023
Epoch 15/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m213s[0m 7s/step - accuracy: 0.9427 - loss: 0.1562 - val_accuracy: 0.9792 - val_loss: 0.1107
Epoch 16/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m211s[0m 7s/step - accuracy: 0.9677 - loss: 0.0913 - val_accuracy: 0.9667 - val_loss: 0.0881
Epoch 17/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m213s[0m 7s/step - accuracy: 0.9885 - loss: 0.0371 - val_accuracy: 0.9708 - val_loss: 0.1165
Epoch 18/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.9885 - loss: 0.0323 - val_accuracy: 0.9083 - val_loss: 0.3006
Epoch 19/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m212s[0m 7s/step - accuracy: 0.9583 - loss: 0.1306 - val_accuracy: 0.7167 - val_loss: 1.0718
Epoch 20/20
[1m30/30[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m211s[0m 7s/step - accuracy: 0.8260 - loss: 0.3963 - val_accuracy: 0.9583 - val_loss: 0.1117

六、可视化结果

from datetime import datetime
current_time = datetime.now() # 获取当前时间

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.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效

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()

在这里插入图片描述

自我评价
完成了咖啡豆识别项目，从数据加载、预处理，到搭建 VGG-16 网络、调试模型，一步步把理论知识落地成了可运行的代码。我能独立完成完整的图像分类流程，遇到报错会主动排查、修改优化，学习态度踏实，动手能力也有明显提升。训练中我认真对照要求完成任务，耐心调试参数，遇到问题不轻易放弃，也能及时纠正代码错误。整体做事认真细心，有较强的自主学习能力，愿意沉下心钻研深度学习相关内容，后续也会继续夯实基础，不断提升自己的建模和实战能力

# 深度学习 # python # 人工智能
Logo
AtomGit开源社区

AtomGit 是由开放原子开源基金会联合 CSDN 等生态伙伴共同推出的新一代开源与人工智能协作平台。平台坚持“开放、中立、公益”的理念，把代码托管、模型共享、数据集托管、智能体开发体验和算力服务整合在一起，为开发者提供从开发、训练到部署的一站式体验。

更多推荐

cover

AtomGit 首发开源｜光轮智能发布全球首个十万小时级全模态人类行为开源数据集 EgoSuite-Open100K

avatar AtomGit开源社区
cover

构筑赋能金融行业应用 Agent｜20 强决战北京，一场金融 Agent 的硬核答卷

avatar AtomGit开源社区
cover

最高赢取价值万元大奖，仓颉生态创新开发挑战赛开启！

avatar AtomGit开源社区