[人工智能]深度学习·猫狗识别实验 tensorflow 2.0

环境：Python 3.8.8 64-bit; VS Code; tensorflow 2.0
数据集：https://momodel.cn/explore/60e6b9babb5ba072ad72755d?type=dataset
文件结构：

使用GPU加速训练：

然而我的输出为0，只能用CPU，寄！

• 卷积层和池化层的区别？

略。
卷积层主要提取图像特征（F不宜过大，否则参数数量过多），池化层用来缩放图像。

• 卷积核的深度和个数？

train.py

from keras import layers, models, utils, optimizers
from keras.preprocessing.image import ImageDataGenerator
import tensorflow as tf
import os

def define_cnn_model():

    model = models.Sequential()
    # 卷积层
    model.add(layers.Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(200, 200, 3)))
    # 最大池化层
    model.add(layers.MaxPooling2D((2, 2)))
    # Flatten层
    model.add(layers.Flatten())
    # 全连接层
    model.add(layers.Dense(128, activation='relu'))
    model.add(layers.Dense(1, activation='sigmoid'))

    # 编译模型
    opt = optimizers.SGD(lr=0.03, momentum=0.9)
    model.compile(
        optimizer = opt,
        loss = 'binary_crossentropy',
        metrics = ['accuracy']
    )

    return model

def train_cnn_model():
    model = define_cnn_model()
    # 创建图片生成器
    datagen = ImageDataGenerator(rescale = 1.0 / 255.0)
    train_it = datagen.flow_from_directory(
        "ma1ogo3ushu4ju4ji2/dogs_cats/data/train",
        class_mode = 'binary',
        batch_size = 64,
        target_size = (200, 200)
    )
    model.fit_generator(train_it, steps_per_epoch=len(train_it), epochs=30, verbose=1)
    return model

print('文件当前路径：', os.getcwd())
print('开始训练')
model = train_cnn_model()
print('训练结束')
print('开始存储模型')
model.save('ma1ogo3ushu4ju4ji2/myModel.h5')
print('模型存储完毕')

test.py

import keras
import os, random
import matplotlib
from matplotlib.pyplot import imshow
import numpy as np
from PIL import Image
from keras.preprocessing import image

def read_random_image():
    folder = r"ma1ogo3ushu4ju4ji2/dogs_cats/data/test/"
    file_path = folder + random.choice(os.listdir(folder))
    pil_im = Image.open(file_path, 'r')
    return pil_im

def get_predict(pil_im, model):
    # 图片缩放
    pil_im = pil_im.resize((200, 200))
    # 将图片转为 numpy array 格式
    array_im = image.img_to_array(pil_im)
    array_im = np.expand_dims(pil_im, axis=0)
    # 对图片进行预测
    result = model.predict([[array_im]])
    if result[0][0] > 0.5:
        print('预测结果：狗')
    else:
        print('预测结果：猫')

# model = keras.models.load_model('ma1ogo3ushu4ju4ji2/myModel.h5')
model = keras.models.load_model("ma1ogo3ushu4ju4ji2/dogs_cats/model/basic_cnn_model.h5")
pil_im = read_random_image()
pil_im.show()
#imshow(image.img_to_array(pil_im))
get_predict(pil_im, model)

运行结果：


我的评价是：感觉不如瞎猜……准确度。

当然可以通过改进模型或者增大epochs来尝试提高accuracy，不过我没有GPU，就不折腾了，训练时间实在是太长了，代码一会上传到Github，大家有兴趣可以自己尝试。

>> Github传送门