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_ON
GPU_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
_________________________________________________________________
