e96031413

// 每60分钟自动运行代码刷新，解除90分钟断开限制.

// 使用方法：colab页面按下 F12或者 Ctrl+Shift+I (mac按 Option+Command+I) 在console（控制台） 输入以下代码并回车.

// 复制以下代码粘贴在浏览器console！！不要关闭浏览器以免失效
function ConnectButton(){
    console.log("Connect pushed"); 
    document.querySelector("#connect").click() 
}
setInterval(ConnectButton,60000);

e96031413

import matplotlib.pyplot as plt
import numpy as np
import rawpy

def pack_raw(raw):
        im = raw.raw_image_visible.astype(np.float32)
        im = np.expand_dims(im, axis=2)
        img_shape = im.shape
        H = img_shape[0]
        W = img_shape[1]

e96031413

import os
import cv2
import numpy as np
from tqdm import tqdm
import argparse

from facenet_pytorch import MTCNN

mtcnn = MTCNN(select_largest=True, min_face_size=64, post_process=False, device='cuda:0')

e96031413

curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
python3 get-pip.py

echo 'export PATH="$PATH:/home/Yanwei_Liu/.local/bin"' >> ~/.bashrc
echo 'alias python=python3' >> ~/.bashrc
source ~/.bashrc

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt

e96031413

import re
import os

urls = "https://drive.google.com/file/d/FILEID_1/view?usp=drive_link, https://drive.google.com/file/d/FILEID_2/view?usp=drive_link, https://drive.google.com/file/d/FILEID_3/view?usp=drive_link"
url_list = urls.split(', ')
pat = re.compile('https://drive.google.com/file/d/(.*)/view\?usp=drive_link')
for idx, url in enumerate(url_list):
    g = pat.match(url)
    id = g.group(1)
    down_url = f'https://drive.google.com/uc?id={id}'

e96031413

'''
Firebase是可以即時讀取的資料庫，主要以JSON格式為主。除了透過程式操作外，也能在Firebase的網頁界面上進行資料操作(上傳、讀取、修改、刪除)
'''

###程式1###


#引入模組
from firebase import firebase
import time

e96031413

"""
https://github.com/d246810g2000/YOLOX/blob/main/datasets/train_val_data_split_coco.py
"""
import os
import cv2
import json
import random
import shutil
import xml.etree.ElementTree as ET
from tqdm import tqdm

e96031413

def resume_train(self, model):
    if self.args.resume:
        logger.info("resume training")
        if self.args.ckpt is None:
            ckpt_file = os.path.join(self.file_name, "latest" + "_ckpt.pth")
        else:
            ckpt_file = self.args.ckpt

        ckpt = torch.load(ckpt_file, map_location=self.device)
        # resume the model/optimizer state dict

e96031413

def _cache_images(self):
    logger.warning("\n********************************************************************************\n"
                   "You are using cached images in RAM to accelerate training.\n"
                   "This requires large system RAM.\n"
                   "Make sure you have 200G+ RAM and 136G available disk space for training COCO.\n"
                   "********************************************************************************\n")
    max_h = self.img_size[0]
    max_w = self.img_size[1]
    cache_file = self.data_dir + "/img_resized_cache_" + self.name + ".array"
    if not os.path.exists(cache_file):

e96031413

"""
https://github.com/z-bingo/FastDVDNet/tree/master/arch
Reimplementation of 4 channel FastDVDNet in PyTorch
"""
import torch
import torch.nn as nn
import numpy as np
from thop import profile