sbarratt

def get_jacobian(net, x, noutputs):
    x = x.squeeze()
    n = x.size()[0]
    x = x.repeat(noutputs, 1)
    x.requires_grad_(True)
    y = net(x)
    y.backward(torch.eye(noutputs))
    return x.grad.data

johnhw

### 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

InnovArul

import torch, torch.nn as nn, torch.nn.functional as F
import numpy as np
import torch.optim as optim

# tied autoencoder using off the shelf nn modules
class TiedAutoEncoderOffTheShelf(nn.Module):
    def __init__(self, inp, out, weight):
        super().__init__()
        self.encoder = nn.Linear(inp, out, bias=False)
        self.decoder = nn.Linear(out, inp, bias=False)

Tushar-N

import torch
import torch.nn as nn
import torch.nn.functional as F

import torchvision.models as tmodels
from functools import partial
import collections

# dummy data: 10 batches of images with batch size 16
dataset = [torch.rand(16,3,224,224).cuda() for _ in range(10)]

doctorpangloss

pjspillai

OS: Ubuntu 18.04
Others: Opencv, NCCL, CUDA 9.2, CUDNN

NOTE: For Ubuntu 17.04/ 18.04, there's an alternate way to directly install Caffe via apt-get install caffe-cpu and caffe-cuda
I am installing from source so that I can with other caffe algorithms that demand the existence of a CAFFE_ROOT directory


Modify Makefile.config file
--------------------

gaearon

If you haven’t worked with JavaScript in the last few years, these three points should give you enough knowledge to feel comfortable reading the React documentation:

• We define variables with let and const statements. For the purposes of the React documentation, you can consider them equivalent to var.
• We use the class keyword to define JavaScript classes. There are two things worth remembering about them. Firstly, unlike with objects, you don't need to put commas between class method definitions. Secondly, unlike many other languages with classes, in JavaScript the value of this in a method [depends on how it is called](https://developer.mozilla.org/en-US/docs/Web/Jav

ppope

"""
preprocess-twitter.py

python preprocess-twitter.py "Some random text with #hashtags, @mentions and http://t.co/kdjfkdjf (links). :)"

Script for preprocessing tweets by Romain Paulus
with small modifications by Jeffrey Pennington
with translation to Python by Motoki Wu

Translation of Ruby script to create features for GloVe vectors for Twitter data.

goerz

This gist contains out.tex, a tex file that adds a PDF outline ("bookmarks") to the freely available pdf file of the book

The Elements of Statistical Learning (2nd ed), by Trevor Hastie, Robert Tibshirani, and Jerome Friedman

https://web.stanford.edu/~hastie/ElemStatLearn/

The bookmarks allow to navigate the contents of the book while reading it on a screen.

Usage

xmfbit

import os
import torch
import torch.nn as nn
from torch.autograd import Variable
import torchvision.datasets as dset
import torchvision.transforms as transforms
import torch.nn.functional as F
import torch.optim as optim
## load mnist dataset
use_cuda = torch.cuda.is_available()