stephenroller

#!/usr/bin/env python3

"""
Example of a generic Mixout implementation. (Lee et al., 2019).
https://arxiv.org/abs/1909.11299

Implementation by Stephen Roller (https://stephenroller.com).

Updated 2020-02-10 to include 1/(1 - p) correction term. Thanks to
Cheolhyoung Lee for making this correction.

redknightlois

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)

y0ast

Now available here: https://github.com/y0ast/pytorch-snippets/tree/main/fast_mnist

thomwolf

# 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

thomwolf

def top_k_top_p_filtering(logits, top_k=0, top_p=0.0, filter_value=-float('Inf')):
    """ Filter a distribution of logits using top-k and/or nucleus (top-p) filtering
        Args:
            logits: logits distribution shape (vocabulary size)
            top_k >0: keep only top k tokens with highest probability (top-k filtering).
            top_p >0.0: keep the top tokens with cumulative probability >= top_p (nucleus filtering).
                Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)
    """
    assert logits.dim() == 1  # batch size 1 for now - could be updated for more but the code would be less clear
    top_k = min(top_k, logits.size(-1))  # Safety check

Bleuje

// by Etienne JACOB
// uses a formula inspired by @ozachou_g (on twitter)

//click on canvas to generate a new one
//press key to save

float x,y,z,t;

float[] A = new float[12];
float[] f = new float[12];

seanjtaylor

zeyademam

Troubleshooting Convolutional Neural Networks

Intro

This is a list of hacks gathered primarily from prior experiences as well as online sources (most notably Stanford's CS231n course notes) on how to troubleshoot the performance of a convolutional neural network . We will focus mainly on supervised learning using deep neural networks. While this guide assumes the user is coding in Python3.6 using tensorflow (TF), it can still be helpful as a language agnostic guide.

Suppose we are given a convolutional neural network to train and evaluate and assume the evaluation results are worse than expected. The following are steps to troubleshoot and potentially improve performance. The first section corresponds to must-do's and generally good practices before you start troubleshooting. Every subsequent section header corresponds to a problem and the section is devoted to solving it. The sections are ordered to reflect "more common" issues first and under each header the "most-eas

genekogan

for i in {1..100}; do 
	filepath=$(printf "http://caliban.mpipz.mpg.de/haeckel/kunstformen/Tafel_%03d_300.jpg" $i)
	wget $filepath; 
done

beesandbombs

int[][] result;
float t, c;

float ease(float p) {
  return 3*p*p - 2*p*p*p;
}

float ease(float p, float g) {
  if (p < 0.5) 
    return 0.5 * pow(2*p, g);