【人工智能项目】- 深度学习实现猫狗大战

【人工智能项目】- 深度学习实现猫狗大战

本次实现猫狗大战，实质上就是猫狗的二分类任务。

环境

!nvidia-smi

Mon Jun 22 04:24:29 2020       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 450.36.06    Driver Version: 418.67       CUDA Version: 10.1     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Tesla K80           Off  | 00000000:00:04.0 Off |                    0 |
| N/A   38C    P8    26W / 149W |      0MiB / 11441MiB |      0%      Default |
|                               |                      |                 ERR! |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

!unzip cats_and_dogs.zip

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import os
import time
import datetime
import sys
import glob

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.utils import class_weight as cw

from keras import Sequential

from keras.models import Model

from keras.layers import LSTM,Activation,Dense,Dropout,Input,Embedding,BatchNormalization,Add,concatenate,Flatten
from keras.layers import Conv1D,Conv2D,Convolution1D,MaxPool1D,SeparableConv1D,SpatialDropout1D,GlobalAvgPool1D,GlobalMaxPool1D,GlobalMaxPooling1D
from keras.layers.pooling import _GlobalPooling1D
from keras.layers import MaxPooling2D,GlobalMaxPooling2D,GlobalAveragePooling2D

from keras.optimizers import RMSprop,Adam

from keras.preprocessing.text import Tokenizer
from keras.preprocessing import sequence

from keras.utils import to_categorical

from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint
from keras.callbacks import ReduceLROnPlateau


from keras import __version__
from keras.applications.inception_v3 import InceptionV3, preprocess_input
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam

%matplotlib inline

import warnings
warnings.filterwarnings("ignore")

/usr/local/lib/python3.6/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.
  import pandas.util.testing as tm
Using TensorFlow backend.

读取数据

img_width,img_height = 299, 299    #修正 InceptionV3 的尺寸参数
epochs = 5
batch_size = 32
fc_size = 1024

def get_nb_files(directory):
    """Get number of files by searching directory recursively"""
    if not os.path.exists(directory):
        return 0
    cnt = 0
    for r, dirs, files in os.walk(directory):
        for dr in dirs:
            cnt += len(glob.glob(os.path.join(r, dr + "/*")))       # glob模块是用来查找匹配文件的，后面接匹配规则。
    return cnt
    
# 定义增加最后一个全连接层的函数
def add_new_last_layer(base_model, nb_classes):
    """Add last layer to the convnet

    Args:
        base_model: keras model excluding top
        nb_classes: # of classes

    Returns:
        new keras model with last layer
    """
    x = base_model.output
    x = GlobalAveragePooling2D()(x)
    x = Dense(fc_size, activation='relu')(x) #new FC layer, random init
    predictions = Dense(nb_classes, activation='softmax')(x) #new softmax layer
    model = Model(inputs=base_model.input, outputs=predictions)
    return model

# 定义微调函数
def setup_to_finetune(model):
    """Freeze the bottom NB_IV3_LAYERS and retrain the remaining top layers.

        note: NB_IV3_LAYERS corresponds to the top 2 inception blocks in the inceptionv3 arch

    Args:
        model: keras model
    """
    # for layer in model.layers[:NB_IV3_LAYERS_TO_FREEZE]:
    #     layer.trainable = False
    for layer in model.layers[:]:
        layer.trainable = True
    model.compile(optimizer=Adam(lr=0.0001), loss='categorical_crossentropy', metrics=['accuracy'])

train_dir= "./train"
valid_dir = "./validation"
nb_classes = len(glob.glob(train_dir + "/*"))
# nb_val_samples = get_nb_files(val_dir)
epochs = int(epochs)
batch_size = int(batch_size)

train_data = ImageDataGenerator(
    # 浮点数，剪切强度（逆时针方向的剪切变换角度）
    shear_range=0.1,
    # 随机缩放的幅度，若为浮点数，则相当于[lower,upper] = [1 - zoom_range, 1+zoom_range]
    zoom_range=0.1,
    # 浮点数，图片宽度的某个比例，数据提升时图片水平偏移的幅度
    width_shift_range=0.1,
    # 浮点数，图片高度的某个比例，数据提升时图片竖直偏移的幅度
    height_shift_range=0.1,
    # 布尔值，进行随机水平翻转
    horizontal_flip=True,
    # 布尔值，进行随机竖直翻转
    vertical_flip=True,
    # 在 0 和 1 之间浮动。用作验证集的训练数据的比例
#         validation_split=0.3
    )

# 接下来生成验证集，可以参考训练集的写法
validation_data = ImageDataGenerator(
    # 浮点数，剪切强度（逆时针方向的剪切变换角度）
    shear_range=0.1,
    # 随机缩放的幅度，若为浮点数，则相当于[lower,upper] = [1 - zoom_range, 1+zoom_range]
    zoom_range=0.1,
    # 浮点数，图片宽度的某个比例，数据提升时图片水平偏移的幅度
    width_shift_range=0.1,
    # 浮点数，图片高度的某个比例，数据提升时图片竖直偏移的幅度
    height_shift_range=0.1,
    # 布尔值，进行随机水平翻转
    horizontal_flip=True,
    # 布尔值，进行随机竖直翻转
    vertical_flip=True,
)

train_generator = train_data.flow_from_directory(
    # 提供的路径下面需要有子目录
    train_dir,
    # 整数元组 (height, width)，默认：(256, 256)。 所有的图像将被调整到的尺寸。
    target_size=(299,299),
    # 一批数据的大小
    batch_size=batch_size,
    # "categorical", "binary", "sparse", "input" 或 None 之一。
    # 默认："categorical",返回one-hot 编码标签。
    class_mode='categorical',
    seed=0)

validation_generator = train_data.flow_from_directory(
    valid_dir,
    target_size=(299,299),
    batch_size=batch_size,
    class_mode='categorical',
    seed=0)

Found 1800 images belonging to 2 classes.
Found 600 images belonging to 2 classes.

模型准备

# 准备跑起来，首先给 base_model 和 model 赋值，迁移学习和微调都是使用 InceptionV3 的 notop 模型（看 inception_v3.py 源码，此模型是打开了最后一个全连接层），利用 add_new_last_layer 函数增加最后一个全连接层。

base_model = InceptionV3(weights="imagenet", include_top=False)  # include_top=False excludes final FC layer
model = add_new_last_layer(base_model, nb_classes)


print("开始微调:\n")

# fine-tuning
setup_to_finetune(model)

Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5
87916544/87910968 [==============================] - 1s 0us/step
开始微调:

model.summary()

Model: "model_1"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            (None, None, None, 3 0                                            
__________________________________________________________________________________________________
conv2d_1 (Conv2D)               (None, None, None, 3 864         input_1[0][0]                    
__________________________________________________________________________________________________
batch_normalization_1 (BatchNor (None, None, None, 3 96          conv2d_1[0][0]                   
__________________________________________________________________________________________________
activation_1 (Activation)       (None, None, None, 3 0           batch_normalization_1[0][0]      
__________________________________________________________________________________________________
conv2d_2 (Conv2D)               (None, None, None, 3 9216        activation_1[0][0]               
__________________________________________________________________________________________________
batch_normalization_2 (BatchNor (None, None, None, 3 96          conv2d_2[0][0]                   
__________________________________________________________________________________________________
activation_2 (Activation)       (None, None, None, 3 0           batch_normalization_2[0][0]      
__________________________________________________________________________________________________
conv2d_3 (Conv2D)               (None, None, None, 6 18432       activation_2[0][0]               
__________________________________________________________________________________________________
batch_normalization_3 (BatchNor (None, None, None, 6 192         conv2d_3[0][0]                   
__________________________________________________________________________________________________
activation_3 (Activation)       (None, None, None, 6 0           batch_normalization_3[0][0]      
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D)  (None, None, None, 6 0           activation_3[0][0]               
__________________________________________________________________________________________________
conv2d_4 (Conv2D)               (None, None, None, 8 5120        max_pooling2d_1[0][0]            
__________________________________________________________________________________________________
batch_normalization_4 (BatchNor (None, None, None, 8 240         conv2d_4[0][0]                   
 
__________________________________________________________________________________________________
global_average_pooling2d_1 (Glo (None, 2048)         0           mixed10[0][0]                    
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 1024)         2098176     global_average_pooling2d_1[0][0] 
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 2)            2050        dense_1[0][0]                    
==================================================================================================
Total params: 23,903,010
Trainable params: 23,868,578
Non-trainable params: 34,432
__________________________________________________________________________________________________

print("Setting Callbacks")

checkpoint = ModelCheckpoint("model.h5",
                                                     monitor="val_loss",
                                                     save_best_only=True,
                                                     mode="min")

early_stopping = EarlyStopping(monitor="val_loss",
                                                     patience=3,
                                                     verbose=1,
                                                     restore_best_weights=True,
                                                     mode="min")

reduce_lr = ReduceLROnPlateau(monitor="val_loss",
                                                      factor=0.6,
                                                      patience=2,
                                                      verbose=1,
                                                      mode="min")

callbacks=[checkpoint,early_stopping,reduce_lr]

Setting Callbacks

训练

history_ft = model.fit_generator(
    train_generator,
    steps_per_epoch=1800   // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=600    // batch_size,
    callbacks=callbacks)

Epoch 1/20
56/56 [==============================] - 139s 2s/step - loss: 0.1774 - accuracy: 0.9259 - val_loss: 0.0389 - val_accuracy: 0.9358
Epoch 2/20
56/56 [==============================] - 99s 2s/step - loss: 0.0824 - accuracy: 0.9729 - val_loss: 0.1625 - val_accuracy: 0.9648
Epoch 3/20
56/56 [==============================] - 98s 2s/step - loss: 0.0448 - accuracy: 0.9825 - val_loss: 0.0261 - val_accuracy: 0.9577
Epoch 4/20
56/56 [==============================] - 98s 2s/step - loss: 0.0432 - accuracy: 0.9898 - val_loss: 0.1232 - val_accuracy: 0.9789
Epoch 5/20
56/56 [==============================] - 97s 2s/step - loss: 0.0311 - accuracy: 0.9893 - val_loss: 0.1762 - val_accuracy: 0.9366

Epoch 00005: ReduceLROnPlateau reducing learning rate to 5.999999848427251e-05.
Epoch 6/20
56/56 [==============================] - 96s 2s/step - loss: 0.0182 - accuracy: 0.9926 - val_loss: 0.4272 - val_accuracy: 0.9630
Restoring model weights from the end of the best epoch
Epoch 00006: early stopping

展示

# 画曲线
def plot_performance(history=None,figure_directory=None,ylim_pad=[0,0]):
    xlabel="Epoch"
    legends=["Training","Validation"]
    
    plt.figure(figsize=(20,5))
    
    y1=history.history["accuracy"]
    y2=history.history["val_accuracy"]
    
    min_y=min(min(y1),min(y2))-ylim_pad[0]
    max_y=max(max(y1),max(y2))+ylim_pad[0]
    
    plt.subplot(121)
    
    plt.plot(y1)
    plt.plot(y2)
    
    plt.title("Model Accuracy\n",fontsize=17)
    plt.xlabel(xlabel,fontsize=15)
    plt.ylabel("Accuracy",fontsize=15)
    plt.ylim(min_y,max_y)
    plt.legend(legends,loc="upper left")
    plt.grid()
    
    y1=history.history["loss"]
    y2=history.history["val_loss"]
    
    min_y=min(min(y1),min(y2))-ylim_pad[1]
    max_y=max(max(y1),max(y2))+ylim_pad[1]
    
    plt.subplot(122)
    
    plt.plot(y1)
    plt.plot(y2)
    
    plt.title("Model Loss:\n",fontsize=17)
    plt.xlabel(xlabel,fontsize=15)
    plt.ylabel("Loss",fontsize=15)
    plt.ylim(min_y,max_y)
    plt.legend(legends,loc="upper left")
    plt.grid()
    plt.show()

plot_performance(history_ft)

import numpy as np
import pandas as pd
import os
import random
import matplotlib.pyplot as plt
from keras import regularizers
from PIL import Image
from tensorflow.keras.preprocessing import image
import glob
# Image processing
from PIL import Image, ImageFile
from keras.preprocessing import image
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from keras.layers import Dropout
from keras.layers import BatchNormalization
from keras.callbacks import EarlyStopping
import keras.backend as K
from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPool2D, Flatten
from keras.layers import Activation, Dense
from keras.utils.np_utils import to_categorical
from keras.optimizers import SGD, Adam, Adagrad, RMSprop
from sklearn.metrics import confusion_matrix
import seaborn as sns
import tensorflow as tf
from keras.models import load_model
from keras.preprocessing import image
from sklearn.metrics import accuracy_score

true=[]
pred=[]

garbage_types = ['cats','dogs']
labels = {
     0:'cats',1:'dogs'}

model_path = 'model.h5'
model = load_model(model_path)

for garbage in garbage_types:
    files = glob.glob("./test/" + str(garbage) + "/*.jpg")
    for myFile in files:
        t = list(labels.keys())[list(labels.values()).index(str(garbage))]
        true.append(t)
        img = image.load_img(myFile,target_size=(224,224))
        input_image = image.img_to_array(img)
        
    
        # 加载模型,加载请注意 model_path 是相对路径, 与当前文件同级。
        # 如果你的模型是在 results 文件夹下的 dnn.h5 模型，则 model_path = 'results/dnn.h5'
        # -------------------------- 实现模型预测部分的代码 ---------------------------
        # expand_dims的作用是把img.shape转换成(1, img.shape[0], img.shape[1], img.shape[2])
        x = np.expand_dims(img, axis=0)
     # 模型预测
        y = model.predict(x)
        predict = labels[np.argmax(y)]
        pred.append(np.argmax(y))


acc = accuracy_score(true,pred)
print(acc)
con_matrix = confusion_matrix(true, pred,
                              labels=[0, 1])
plt.figure(figsize=(10, 10))
plt.title('Prediction of garbage types')
plt.ylabel('True label')
plt.xlabel('Predicted label')
# plt.show(sns.heatmap(con_matrix, annot=True, fmt="d",annot_kws={"size": 7},cmap='Blues',square=True))
ax = sns.heatmap(con_matrix, annot=True, fmt="d", annot_kws={
     "size": 7}, cmap='Blues', square=True)
bottom, top = ax.get_ylim()
ax.set_ylim(bottom + 0.5, top - 0.5)
plt.show()

0.9716666666666667

小结

本次就用迁移学习的方式完成猫狗二分类任务，很简单的任务。
瓷们，还是点赞收藏评论走起来！！！