>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/0dvHCaOoFnW8SCp3JpzKxg) 中的学习记录博客**
>- **🍖 原作者:[K同学啊](https://mtyjkh.blog.csdn.net/)**
一、前言:
本次包含了vgg16的官方模型和自建模型,在我的理解下,官方模型貌似不能很容易的增加或删除某些层,所以在日后可能会加上一些轻量化的内容(虽然100%准确率还没解决hhh)
二、一如即往的先导包导数据:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, models
import PIL, pathlib
import matplotlib.pyplot as plt
import numpy as np
data_dir = "/kaggle/input/dataset2"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob("*/*.png")))
print(image_count)
batch_size = 32
img_height = 224
img_wdith = 224
train_ds = keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split = 0.2,
subset = "training",
seed = 123,
batch_size = batch_size,
image_size = (img_height, img_wdith)
)
val_ds = keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split = 0.2,
subset = "validation",
seed = 123,
batch_size = batch_size,
image_size = (img_height, img_wdith)
)
class_names = train_ds.class_names
print(class_names)
plt.figure(figsize = (20, 10))
for image, labels in train_ds.take(1):
for i in range(20):
plt.subplot(5, 10, i+1)
plt.imshow(image[i].numpy().astype("uint8"))
plt.title(class_names[labels[i]])
plt.axis("off")
for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break
#输出:
#图片总数:1200
#数据集分割内容:
Found 1200 files belonging to 4 classes. Using 960 files for training. Found 1200 files belonging to 4 classes. Using 240 files for validation.
#类别输出:
['Dark', 'Green', 'Light', 'Medium']
#查看数据集格式:
(32, 224, 224, 3) (32,)
#数据集的样本:
三、配置数据集和归一化:
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size = AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size = AUTOTUNE)
#归一化
normalization_layer = 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))
image_1 = image_batch[0]
print(np.min(image_1), np.max(image_1))
#归一化后的数据内最大为1最小为0 :
0.0 1.0
四、调用官方的vgg16模型
model = tf.keras.applications.VGG16(weights='imagenet')
model.summary()
#输出内容如下:: Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels.h5 553467096/553467096 ━━━━━━━━━━━━━━━━━━━━ 21s 0us/step
Model: "vgg16"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓ ┃ 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, 1000) │ 4,097,000 │ └─────────────────────────────────┴────────────────────────┴───────────────┘
Total params: 138,357,544 (527.79 MB)
Trainable params: 138,357,544 (527.79 MB)
Non-trainable params: 0 (0.00 B)
#两种方法的训练结果放在后面比较
五、自建vgg16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)
x = Dropout(0.3)(x)
output_tensor = Dense(nb_classes, activation='softmax', name='predictions')(x)
model = Model(input_tensor, output_tensor)
return model
model=VGG16(6, (img_wdith, img_height, 3))
model.summary()
#模型summary一下:
Model: "functional_1"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓ ┃ 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 │ ├─────────────────────────────────┼────────────────────────┼───────────────┤ │ dropout (Dropout) │ (None, 4096) │ 0 │ ├─────────────────────────────────┼────────────────────────┼───────────────┤ │ predictions (Dense) │ (None, 6) │ 24,582 │ └─────────────────────────────────┴────────────────────────┴───────────────┘
Total params: 134,285,126 (512.26 MB)
Trainable params: 134,285,126 (512.26 MB)
Non-trainable params: 0 (0.00 B)
六、编译及训练
initial_learning_rate = 0.0001
lr_schedule = keras.optimizers.schedules.ExponentialDecay(
initial_learning_rate,
decay_steps = 20,
decay_rate = 0.92,
staircase = True
)
opt = keras.optimizers.Adam(learning_rate = initial_learning_rate)
model.compile(
optimizer = opt,
loss = keras.losses.SparseCategoricalCrossentropy(from_logits = True),
metrics = ["accuracy"]
)
epochs = 100
history = model.fit(
train_ds,
validation_data = val_ds,
epochs = epochs,
)
七、两种模型的效果比较:
#官方vgg16模型&参数的效果:
#自建的vgg16模型效果:
八、loss和accuracy的曲线:
#官方模型的结果:
#自建模型的结果:
九、总结:
总结一下还是预训练的模型好用,调半天不如直接调,,,日后的方向可以在预训练参数的基础上着手提高准确率,最近会试试测试准确能不能到达100%,然后的任务是对vgg16进行轻量化。