- 🍨 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