Skip to content

Instantly share code, notes, and snippets.

View NataliaDiaz's full-sized avatar
💭
Working on responsible AI systems

Natalia Díaz Rodríguez NataliaDiaz

💭
Working on responsible AI systems
444 followers · 1.1k following
View GitHub Profile
@ClementPinard
ClementPinard / Still_Box_README.md
Last active September 19, 2017 10:58
Still Box README

Still Box

Torrent description

In addition to this README, this torrent contains 4 datasets:

Name Image size (px) Scene number Size compressed (B) Total size (B)
64.tar.xz 64x64 80K 9.8G 19G
128.tar.xz 128x128 20K 7.1G 12G
@audy
audy / fuckinginstallmatplotlibscipynumpysklearnipython_mountain_lion.md
Last active November 6, 2017 12:42
How to fucking install matplotlib, scipy, numpy, scikit learn and ipython notebook on Mountain Lion
@wdevazelhes
wdevazelhes / kernel_attention.py
Last active June 9, 2019 18:43
trying to use kernel approximations by explicit feature maps for softmax self-attention
import numpy as np
from sklearn.utils.extmath import softmax
from sklearn.kernel_approximation import RBFSampler
from sklearn_extra.kernel_approximation import Fastfood
seed = 42
rng = np.random.RandomState(seed)
D = 20
@SiestaMadokaist
SiestaMadokaist / SummedAreaTable.py
Last active November 17, 2020 10:46
Implementation of summed area table / integral image in python.
class SummedAreaTable(object):
def __init__(self, size, data):
"""
Just because I dislike a 2d array / list.
data should be a List of Integer.
"""
width, height = size
assert width * height == len(data), "invalid data length and or data size"
self.size = size
self.data = data
@culurciello
culurciello / xception.lua
Last active March 13, 2021 09:06
-- Xception model
-- a Torch7 implementation of: https://arxiv.org/abs/1610.02357
-- E. Culurciello, October 2016
require 'nn'
local nClasses = 1000
function nn.SpatialSeparableConvolution(nInputPlane, nOutputPlane, kW, kH)
local block = nn.Sequential()
block:add(nn.SpatialConvolutionMap(nn.tables.oneToOne(nInputPlane), kW,kH, 1,1, 1,1))
@minrk
minrk / remove_output.py
Created September 14, 2012 04:45
"""
usage: python remove_output.py notebook.ipynb [ > without_output.ipynb ]
"""
import sys
import io
from IPython.nbformat import current
@anikalindtner
anikalindtner / gist:9524950
Last active March 1, 2023 11:52
Workshops/Mailinglists/Lists
@zaemiel
zaemiel / How to link Sublime Text Build system to Python 3
Last active April 4, 2023 21:32
1. Go to Sublime Text to: Tools -> Build System -> New Build System
and put the next lines:
{
"cmd": ["python3", "-i", "-u", "$file"],
"file_regex": "^[ ]File \"(...?)\", line ([0-9]*)",
"selector": "source.python"
}
Then save it with a meaningful name like: python3.sublime-build
@baraldilorenzo
baraldilorenzo / readme.md
Last active November 21, 2023 22:41
VGG-16 pre-trained model for Keras

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

@fchollet
fchollet / classifier_from_little_data_script_1.py
Last active November 28, 2023 07:12
Updated to the Keras 2.0 API.
'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats