机器学习-python日记

操作系统：MacOS

运行环境：anaconda-Navigator  /  spyder

1. 抓图下载

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import requests
from bs4 import BeautifulSoup
import os
import traceback

print(os.path)

def download(url, filename):
    if os.path.exists(filename):
        print('file exists!')
        return
    try:
        r = requests.get(url, stream=True, timeout=60)
        r.raise_for_status()
        with open(filename, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024):
                if chunk:
                    f.write(chunk)
                    f.flush()
        return filename
    except KeyboardInterrupt:
        if os.path.exists(filename):
            os.remove(filename)
        raise KeyboardInterrupt
    except Exception:
        traceback.print_exc()
        if os.path.exists(filename):
            os.remove(filename)


if os.path.exists('imgs') is False:
    os.makedirs('imgs')

start = 1
end = 8000
for i in range(start, end + 1):
    url = 'http://konachan.net/post?page=%d&tags=' % i
    html = requests.get(url).text
    soup = BeautifulSoup(html, 'html.parser')
    for img in soup.find_all('img', class_="preview"):
        target_url = 'http:' + img['src']
        filename = os.path.join('imgs', target_url.split('/')[-1])
        download(target_url, filename)
    print('%d / %d' % (i, end))

2. 截取头像 使用github上一个基于opencv的工具：点击打开链接

import cv2
import sys
import os.path
from glob import glob

def detect(filename, cascade_file="lbpcascade_animeface.xml"):
    if not os.path.isfile(cascade_file):
        raise RuntimeError("%s: not found" % cascade_file)

    cascade = cv2.CascadeClassifier(cascade_file)
    image = cv2.imread(filename)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    gray = cv2.equalizeHist(gray)

    faces = cascade.detectMultiScale(gray,
                                     # detector options
                                     scaleFactor=1.1,
                                     minNeighbors=5,
                                     minSize=(48, 48))
    for i, (x, y, w, h) in enumerate(faces):
        face = image[y: y + h, x:x + w, :]
        face = cv2.resize(face, (96, 96))
        save_filename = '%s-%d.jpg' % (os.path.basename(filename).split('.')[0], i)
        cv2.imwrite("faces/" + save_filename, face)


if __name__ == '__main__':
    if os.path.exists('faces') is False:
        os.makedirs('faces')
    file_list = glob('imgs/*.jpg')
    for filename in file_list:
        detect(filename)

3. 下载轮子（先用anaconda安装tensorflow）点击打开链接

4. 在data文件夹下新建anime文件夹，上面截取的头像放在这个文件夹下5. 运行python-tensorflow环境：

python main.py --image_size 96 --output_size 48 --dataset anime --is_crop True --is_train True --epoch 300 --input_fname_pattern "*.jpg"

--epoch 300  训练300轮
--dataset anime 训练集目录