- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍦 参考文章：[Pytorch实战 | 第J3周：Desnet
- 🍖 原作者：K同学啊|接辅导、项目定制
🏡 我的环境：
● 语言环境：Python 3.8
● 编译器：Google Colab
● 深度学习环境：Tensorflow
一、 前期准备
1. 设置GPU
如果设备上支持GPU就使用GPU,否则使用CPU
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
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显存用量按需使用
tf.config.set_visible_devices([gpu0],"GPU")
gpus
2. 导入数据
本地数据集位于./data/bird_photos/目录下
import os,PIL,random,pathlib
data_dir = r'/content/bird_photos'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[3] for path in data_paths]
classeNames
f = []
for root, dirs, files in os.walk(data_dir):
for name in files:
f.append(os.path.join(root, name))
print("图片总数：",len(f))
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
# transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
total_data = datasets.ImageFolder("./data/7-data/",transform=train_transforms)
total_data.class_to_idx
3. 划分数据集
train_size = int(0.8 * len(total_data))
test_size = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_dataset, test_dataset
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
for X, y in test_dl:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break
4. 显示图片信息
#%%
import matplotlib.pyplot as plt
import numpy as np
def imageshow(images, labels=None):
plt.figure(dpi=100,figsize=(12,4))
for i in range(8):
plt.subplot(3, 3, i+1)
img = images[i].numpy().astype("uint8")
plt.imshow(img)
if labels is not None:
plt.title(train_ds.class_names[labels[i]])
plt.axis('off')
plt.tight_layout(pad=0.5)
plt.show()
dataiter = iter(train_ds)
images, labels = dataiter.next()
imageshow(images, labels)
二、手动搭建Desnet模型
1.模型
2.代码
#%%
''' Residual Block '''
class BottleNeck(keras.Model):
def __init__(self, growth_rate, bn_size = 4, dropout = 0.3):
super().__init__()
self.bn1 = layers.BatchNormalization()
self.relu = layers.Activation("relu"),
self.conv1 = layers.Conv2D(filters=bn_size * growth_rate, kernel_size=(1, 1),
strides=1, padding='same')
self.bn2 = layers.BatchNormalization()
self.conv2 = layers.Conv2D(filters=growth_rate, kernel_size=(3, 3),
strides=1, padding='same')
self.dropout = layers.Dropout(rate=dropout)
self.listLayers = [
self.bn1,
self.relu,
self.conv1,
self.bn2,
self.relu,
self.conv2,
self.dropout
]
def call(self, x):
tem = x
for layer in self.listLayers.layers:
x = layer(x)
return layers.concatenate([tem, x], axis=-1)
class Transition(tf.keras.Model):
def __init__(self, growth_rate):
super().__init__()
self.bn1 = layers.BatchNormalization()
self.relu = layers.Activation('relu')
self.conv1 = layers.Conv2D(filters = growth_rate, kernel_size=(1, 1),
strides = 1, activation = 'relu', padding='same')
self.pooling = layers.AveragePooling2D(pool_size=(2,2), strides = 2,padding='same')
self.listLayers = [
self.bn1,
self.relu,
self.conv1,
self.pooling
]
def call(self,x):
for layer in self.listLayers.layers:
x = layer(x)
return x
class DenseBlock(tf.keras.Model):
def __init__(self, num_layer, growth_rate, bn_size = 4, dropout = 0.3, efficient=False):
super().__init__()
self.efficient = efficient
self.listLayers = []
if self.efficient:
_x = tf.recompute_grad(BottleNeck(growth_rate, bn_size = bn_size, dropout = dropout))
else:_x =BottleNeck(growth_rate, bn_size = bn_size, dropout = dropout)
for _ in range(num_layer):
self.listLayers.append(BottleNeck(growth_rate, bn_size = bn_size, dropout = dropout))
def call(self, x):
for layer in self.listLayers.layers:
x = layer(x)
return x
class DenseNet(tf.keras.Model):
def __init__(self, num_init_feature, growth_rate, block_config, num_classes,
bn_size=4, dropout=0.3, compression_rate=0.5, efficient=False):
super().__init__()
self.num_channels = num_init_feature
self.conv = layers.Conv2D(filters = num_init_feature, kernel_size=7,
strides = 2, padding='same')
self.bn = layers.BatchNormalization()
self.relu = layers.Activation('relu')
self.max_pool = layers.MaxPool2D(pool_size=3, strides=2, padding='same')
self.dense_block_layers = []
for i in block_config[:-1]:
self.dense_block_layers.append( DenseBlock(num_layer =i, growth_rate = growth_rate,
bn_size = bn_size, dropout = dropout, efficient=efficient))
self.num_channels = compression_rate * (self.num_channels + growth_rate * i)
self.dense_block_layers.append( Transition(self.num_channels))
self.dense_block_layers.append( DenseBlock(num_layer =block_config[-1], growth_rate = growth_rate,
bn_size = bn_size, dropout = dropout, efficient=efficient))
self.avgpool = layers.GlobalAveragePooling2D()
self.fc = tf.keras.layers.Dense(units=num_classes, activation=tf.keras.activations.softmax)
def call(self,x):
x = self.conv(x)
x = self.bn(x)
x = self.relu(x)
x = self.max_pool(x)
for layer in self.dense_block_layers.layers:
x = layer(x)
x = self.avgpool(x)
return self.fc(x)
model = DenseNet(num_init_feature=64,
growth_rate=32,
block_config=[6,12,24,16],
compression_rate=0.5,
num_classes = 4,
dropout=0.0,
efficient=True)
x = tf.random.normal((1,224,224,3))
for layer in model.layers:
x = layer(x)
print(layer.name, 'output shape:\t', x.shape)
''' 显示网络结构 '''
三、训练模型
1. 编写训练和测试函数
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
opt = tf.keras.optimizers.legacy.Adam(learning_rate=0.002,decay=0.01)
model.compile(optimizer=opt,
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
epochs = 200
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
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()
2.正式训练
3.指定图片预测
import numpy as np
plt.figure(figsize=(18,3))
plt.suptitle('预测结果展示')
for images,label in val_ds.take(1):
for i in range(8):
ax=plt.subplot(1, 8, i+1)
plt.imshow(images[i].numpy().astype("uint8"))
img_array=tf.expand_dims(images[i],0)
predictions=model.predict(img_array)
plt.title(classeNames[np.argmax(predictions)])
plt.axis('off')
总结
DenseNet相比ResNet，拥有更密集的连接机制:互相连接所有层，即元素叠加。这可以实现特征重用，提高效率。
简单来讲，ResNet是对应位置上进行求和，最终不会改变通道数量的；DenseNet而后者是通道合并，也就是说值不变，直接堆砌在一起
DesNet网络结构:DenseBlock+transistion
DesBlock结构:BN+RELU+3x3Conv
DenseNet-B结构: BN+RELU+1x1+Conv+BN+ReLU+3x3 Conv
Transition结构:BN+ReLU+1x1Conv+2x2 AvgPooling
DenseNet结构（ImageNet数据集)
算法比较：
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
