Skip to content

Instantly share code, notes, and snippets.

View xuanhan863's full-sized avatar
👀
In machine learning...

Slice xuanhan863

👀
In machine learning...
  • Los Angeles, USA
View GitHub Profile
@redknightlois
redknightlois / ralamb.py
Last active August 9, 2023 20:50
Ralamb optimizer (RAdam + LARS trick)
class Ralamb(Optimizer):
def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0):
defaults = dict(lr=lr, betas=betas, eps=eps, weight_decay=weight_decay)
self.buffer = [[None, None, None] for ind in range(10)]
super(Ralamb, self).__init__(params, defaults)
def __setstate__(self, state):
super(Ralamb, self).__setstate__(state)
"""Implementation of NEAT.
python neat.py --task {xor, lunar, cartpole}
See the post at https://wellecks.wordpress.com/ for details.
Parts of this implementation are based on Neat-Python.
"""
from itertools import count
import numpy as np
import math
@bessarabov
bessarabov / gist:674ea13c77fc8128f24b5e3f53b7f094
Last active August 23, 2024 19:11
One-liner to generate data shown in post 'At what time of day does famous programmers work?' — https://ivan.bessarabov.com/blog/famous-programmers-work-time
git log --author="Linus Torvalds" --date=iso | perl -nalE 'if (/^Date:\s+[\d-]{10}\s(\d{2})/) { say $1+0 }' | sort | uniq -c|perl -MList::Util=max -nalE '$h{$F[1]} = $F[0]; }{ $m = max values %h; foreach (0..23) { $h{$_} = 0 if not exists $h{$_} } foreach (sort {$a <=> $b } keys %h) { say sprintf "%02d - %4d %s", $_, $h{$_}, "*"x ($h{$_} / $m * 50); }'
@thomwolf
thomwolf / gpt-2-wikitext-103.py
Last active September 23, 2024 20:23
A very small and self-contained gist to train a GPT-2 transformer model on wikitext-103
# Copyright (c) 2019-present, Thomas Wolf.
# All rights reserved. This source code is licensed under the MIT-style license.
""" A very small and self-contained gist to train a GPT-2 transformer model on wikitext-103 """
import os
from collections import namedtuple
from tqdm import tqdm
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
from ignite.engine import Engine, Events
@johnhw
johnhw / umap_sparse.py
Last active February 26, 2025 10:50
1 million prime UMAP layout
### JHW 2018
import numpy as np
import umap
# This code from the excellent module at:
# https://stackoverflow.com/questions/4643647/fast-prime-factorization-module
import random
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nasimrahaman
nasimrahaman / weighted_cross_entropy.py
Last active November 16, 2023 04:54
Pytorch instance-wise weighted cross-entropy loss
import torch
import torch.nn as nn
def log_sum_exp(x):
# See implementation detail in
# http://timvieira.github.io/blog/post/2014/02/11/exp-normalize-trick/
# b is a shift factor. see link.
# x.size() = [N, C]:
b, _ = torch.max(x, 1)
@aparrish
aparrish / understanding-word-vectors.ipynb
Last active March 10, 2025 03:06
Understanding word vectors: A tutorial for "Reading and Writing Electronic Text," a class I teach at ITP. (Python 2.7) Code examples released under CC0 https://creativecommons.org/choose/zero/, other text released under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@keevee09
keevee09 / Install_openCV_pyenv_OSX.md
Last active December 1, 2016 05:32
November 2016 installation of opencv3 from source into pyenv virtualenv python3.5.2 environment

Installing openCV3 into pyenv virtual env

osx 10.11.6

--

  • install python-3:
$ pyenv install 3.5.2