Skip to content

Instantly share code, notes, and snippets.

View tfriedel's full-sized avatar

Thomas Friedel tfriedel

View GitHub Profile
@DiegoHernanSalazar
DiegoHernanSalazar / L8 Evaluation part I.ipynb
Created February 19, 2024 19:49
OpenAI / DeepLearning.AI. Building Systems with the ChatGpt API, L8: Evaluation part I.
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.
@zeyademam
zeyademam / Troubleshoot-dcnn.md
Last active January 22, 2024 05:54
Troubleshooting Convolutional Neural Nets

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

@carlthome
carlthome / Signal reconstruction from spectrograms.ipynb
Created May 31, 2018 13:53
Try to recover audio from filtered magnitudes when phase information has been lost.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@mokemokechicken
mokemokechicken / keras_mnist_vat.py
Last active October 21, 2020 07:37
Virtual Adversarial Training for MNIST with Keras
# coding: utf8
"""
* VAT: https://arxiv.org/abs/1507.00677
# 参考にしたCode
Original: https://github.com/fchollet/keras/blob/master/examples/mnist_cnn.py
VAT: https://github.com/musyoku/vat/blob/master/vat.py
results example
---------------
@rtt
rtt / tinder-api-documentation.md
Last active June 21, 2024 04:19
Tinder API Documentation

Tinder API documentation

Note: this was written in April/May 2014 and the API may has definitely changed since. I have nothing to do with Tinder, nor its API, and I do not offer any support for anything you may build on top of this. Proceed with caution

http://rsty.org/

I've sniffed most of the Tinder API to see how it works. You can use this to create bots (etc) very trivially. Some example python bot code is here -> https://gist.github.com/rtt/5a2e0cfa638c938cca59 (horribly quick and dirty, you've been warned!)

@Uflex
Uflex / clang-format_config.md
Last active November 3, 2019 16:19
Configuration of clang-format for QtCreator

Clang-format in QtCreator

Edit: QtCreator 3.1 introduced a new plugin called Beautifier that supports clang-format. You still have to install the clang tools separately but you don't have to add them as external tools anymore. The plugin can be configured in the options dialog under the beautifier tab > Clang Format. Add a new style and copy the configuration below without the curly braces.

QtCreator doesn't allow using clang-format by default. Watch QTCREATORBUG-10111 for a better integration. As of today, you should use it as an external tool, either replacing your selection or the entire file. If you choose to replace the file, you will have to save it before launching the tool and QtCreator will reload the file, making it impossible to undo/redo afterwards. If you choose to replace your selection, you often have to select the whole function, otherwise you will lose the indentation; clang-format doesn't seem to k