woctezuma

import requests
from bs4 import BeautifulSoup


def get_my_secret_cookie():
    my_secret_cookie = {
        "SC_AUTH_UID": "30993",
        "SC_DEVICE_CATEGORY": "desktop",
        
        "SC_AUTH": "MY_SECRET_COOKIE", # TODO

woctezuma

# 1. Set up StyleGAN

import dnnlib
import dnnlib.tflib as tflib
import pretrained_networks

network_pkl = 'gdrive:networks/stylegan2-ffhq-config-f.pkl'
_G, _D, Gs = pretrained_networks.load_networks(network_pkl)

Gs_kwargs = dnnlib.EasyDict()

woctezuma

import pretrained_networks
import numpy as np
import dnnlib
import dnnlib.tflib as tflib
import PIL.Image

network_pkl = 'gdrive:networks/stylegan2-ffhq-config-f.pkl'
_, _, Gs = pretrained_networks.load_networks(network_pkl)

rng_seed = 5616

woctezuma

PC Gamer

If you arrived here from a PC Gamer article, I suggest you check the Python source code and one of these rankings:

• original ranking, featured on PC Gamer, based on data downloaded prior to the Steam summer sales.
• updated ranking, using data from June 30, a week after the Steam summer sales have started.

Bug fix regarding ranking based on playtime

Initially, I presented on this Gist page a ranking using playtime as popularity measure. However, as I have kept working on the code, I have found out this ranking likely suffered from a bug. The bug, which is now fixed, resulted in a ranking very similar to the ranking using players total as popularity measure. Thankfully, the ranking featured in the PC Gamer article is bug-free sinc

woctezuma

Reference: https://github.com/xinntao/ESRGAN

Prepare code:

%cd /content
!git clone https://github.com/xinntao/ESRGAN.git

%cd /content/ESRGAN/models
!gdown --id 1TPrz5QKd8DHHt1k8SRtm6tMiPjz_Qene

woctezuma

Reference: https://github.com/yangxy/GPEN

Prepare code:

%pip install ninja

%cd /content
!git clone https://github.com/yangxy/GPEN.git

%cd /content/GPEN/weights

woctezuma

# References:
# - https://gist.github.com/woctezuma/f4faef1210e49ed06cf4725bac60998f
# - https://steamcommunity.com/app/1076200/discussions/0/3070873501572457641/

from collections import Counter
from pathlib import Path

import glob
import os

woctezuma

REGEDIT4

[HKEY_CURRENT_USER\software\LEGO System A/S\Builder's Journey]
"SaveGame0_h1867918426"=hex:41,41,45,41,41,41,44,2F,2F,2F,2F,2F,41,51,41,41,\
  41,41,41,41,41,41,41,4D,41,67,41,41,41,45,5A,42,63,33,4E,6C,62,57,4A,73,65,\
  53,31,44,55,32,68,68,63,6E,41,73,49,46,5A,6C,63,6E,4E,70,62,32,34,39,4D,43,\
  34,77,4C,6A,41,75,4D,43,77,67,51,33,56,73,64,48,56,79,5A,54,31,75,5A,58,56,\
  30,63,6D,46,73,4C,43,42,51,64,57,4A,73,61,57,4E,4C,5A,58,6C,55,62,32,74,6C,\
  62,6A,31,75,64,57,78,73,42,51,45,41,41,41,41,57,52,32,46,74,5A,56,42,79,5A,\
  57,5A,7A,53,57,31,77,62,43,74,54,59,58,5A,6C,52,47,46,30,59,51,55,41,41,41,\

woctezuma

%pip install transformers

Reference: https://huggingface.co/facebook/dino-vits16

from transformers import ViTFeatureExtractor, ViTModel
from PIL import Image
import requests
import torch

woctezuma

Vocabulary

• denoising diffusion probabilistic models (DDPM)
• self-supervised learning (SSL)
• vision transformers (ViT)
• self-attention
• masked language modeling, cf. BERT
• contrastive instance discrimination
• distillation
• ablation study