第T7周：Tensorflow实现咖啡豆识别

• 🍨 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

目标

具体实现

（一）环境

语言环境：Python 3.10
编 译 器: PyCharm
框 架:

（二）具体步骤

1. 使用GPU

--------------------------utils.py-------------------
import tensorflow as tf  
import PIL  
import matplotlib.pyplot as plt  def GPU_ON():  # 查询tensorflow版本  print("Tensorflow Version：", tf.__version__)  # 设置使用GPU  gpus = tf.config.list_physical_devices("GPU")  print(gpus)  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显存按需使用  tf.config.set_visible_devices([gpu0], "GPU")

使用GPU并查看数据

import tensorflow as tf  
from tensorflow import keras  
import numpy as np  
import matplotlib.pyplot as plt  
import os, PIL, pathlib  
from utils import GPU_ONGPU_ON()  data_dir = "./datasets/coffee/"  
data_dir = pathlib.Path(data_dir)  image_count = len(list(data_dir.glob("*/*.png")))  
print("图片总数量为:", image_count)
------------------
图片总数量为: 1200

2. 加载数据

# 加载数据  
batch_size = 32  
img_height, img_width = 224, 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,  
)
--------------------
Found 1200 files belonging to 4 classes.
Using 960 files for training.
Found 1200 files belonging to 4 classes.
Using 240 files for validation.

获取标签：

# 获取标签  
class_names = train_ds.class_names  
print(class_names)
------------------
['Dark', 'Green', 'Light', 'Medium']

可视化数据:

# 可视化数据  
plt.figure(figsize=(10, 10))  
for images, labels in train_ds.take(2):  for i in range(30):  ax = plt.subplot(5, 6, i+1)  plt.imshow(images[i].numpy().astype("uint8"))  plt.title(class_names[labels[i]])  plt.axis("off")  
plt.show()

检查一下数据：

# 检查一下数据  
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

# 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)  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(train_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

4.搭建VGG-16网络

本次准备直接调用官方模型

# 搭建VGG-16网络模型  
model = tf.keras.applications.VGG16(weights="imagenet")  
print(model.summary())
-------------------------------
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels.h5
553467096/553467096 [==============================] - 14s 0us/step
Model: "vgg16"
_________________________________________________________________Layer (type)                Output Shape              Param #   
=================================================================input_1 (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 (Flatten)           (None, 25088)             0         fc1 (Dense)                 (None, 4096)              102764544 fc2 (Dense)                 (None, 4096)              16781312  predictions (Dense)         (None, 1000)              4097000   =================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
_________________________________________________________________

简简单单1亿的参数的模型。哈哈。

编译一下：

# 编译模型  
# 设置初始学习率  
initial_learning_rate = 1e-4  
lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(  initial_learning_rate=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=False),  metrics=['accuracy']  
)

训练模型:

# 训练模型  
epochs = 20  
history = model.fit(  train_ds,  validation_data=val_ds,  epochs=epochs,  
)

训练效果不错，可视化看看：

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()

果然超赞。
改成动态学习率的结果：

opt = tf.keras.optimizers.Adam(learning_rate=lr_schedule)

5. 手动搭建VGG-16模型

VGG-16的网络 有13个卷积层（被5个max-pooling层分割）和3个全连接层（FC），所有卷积层过滤器的大小都是3X3，步长为1，进行padding。5个max-pooling层分别在第2、4、7、10，13卷积层后面。每次进行池化（max-pooling)后，特征图的长宽都缩小一半，但是channel都翻倍了，一直到512。最后三个全连接层大小分别是4096，4096， 1000,我们使用的是咖啡豆识别，根据数据集的类别数量修改最后的分类数量（即从1000改成len(class_names))

-----------------------------
Model: "model"
_________________________________________________________________Layer (type)                Output Shape              Param #   
=================================================================input_1 (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 (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
_________________________________________________________________

（三）总结