aslushnikov

// This injects a box into the page that moves with the mouse;
// Useful for debugging
async function installMouseHelper(page) {
  await page.evaluateOnNewDocument(() => {
    // Install mouse helper only for top-level frame.
    if (window !== window.parent)
      return;
    window.addEventListener('DOMContentLoaded', () => {
      const box = document.createElement('puppeteer-mouse-pointer');
      const styleElement = document.createElement('style');

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

peterroelants

"""Script to illustrate usage of tf.estimator.Estimator in TF v1.3"""
import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data as mnist_data
from tensorflow.contrib import slim
from tensorflow.contrib.learn import ModeKeys
from tensorflow.contrib.learn import learn_runner


# Show debugging output

timehaven

"""akmtdfgen:  A Keras multithreaded dataframe generator.

Works with Python 2.7 and Keras 2.x.

For Python 3.x, need to fiddle with the threadsafe generator code.


Test the generator_from_df() functions by running this file:

    python akmtdfgen.py

swyoon

import numpy as np
import tensorflow as tf

__author__ = "Sangwoong Yoon"

def np_to_tfrecords(X, Y, file_path_prefix, verbose=True):
    """
    Converts a Numpy array (or two Numpy arrays) into a tfrecord file.
    For supervised learning, feed training inputs to X and training labels to Y.
    For unsupervised learning, only feed training inputs to X, and feed None to Y.

erikbern

# Note – this is not a bash script (some of the steps require reboot)
# I named it .sh just so Github does correct syntax highlighting.
#
# This is also available as an AMI in us-east-1 (virginia): ami-cf5028a5
#
# The CUDA part is mostly based on this excellent blog post:
# http://tleyden.github.io/blog/2014/10/25/cuda-6-dot-5-on-aws-gpu-instance-running-ubuntu-14-dot-04/

# Install various packages
sudo apt-get update

baraldilorenzo

##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

wrobstory

Why py.test?

py.test Assertions

IMO, py.test tests read better, because of the assert magic. When comparing two Python objects, py.test performs introspection on them for the comparison. As the end user, you don't really need to care about that; you just need to care that your test suite is much more readable. Compare the following:

def test_my_thing():
    # Assume we make some things we want to compare
    assert expected_list == result_list
 assert expected_set == result_set

syhw

"""
A deep neural network with or w/o dropout in one file.

License: Do What The Fuck You Want to Public License http://www.wtfpl.net/
"""

import numpy, theano, sys, math
from theano import tensor as T
from theano import shared
from theano.tensor.shared_randomstreams import RandomStreams

tsiege

ANNOUNCEMENT

I have moved this over to the Tech Interview Cheat Sheet Repo and has been expanded and even has code challenges you can run and practice against!






\