Author: Deep Learner
Stochastic Scene-Aware Motion Prediction
Stochastic Scene-Aware Motion Prediction [Project Page][Paper] Description This repository contains the training code for MotionNet and GoalNet of SAMP. Installation To install the necessary dependencies run the following command: pip install -r requirements.txt The code has been tested with Python 3.8.10, CUDA 10.0, CuDNN 7.5 and PyTorch 1.7.1 on Ubuntu 20.04. Training Data The training data for MotionNet and GoalNet could be found in the website downloads. Or could be extractedfrom the Unity runtime code. Update
Read more
Automatically remove user join messages when the user leaves the server
Automatically remove user join messages when the user leaves the server. Installation You will need to install poetry to run this bot locally for levelopment, but running in docker is preferred for production deployment. Poetry can be installed using the following command: Windows: py -3 -m pip install poetry. Linux/Mac: python3 -m pip install poetry. To install the dependencies you can then run poetry install in the folder you cloned the repository to. You need to copy .env.example to .env […]
Read more
Compare neural networks by their feature similarity
A tiny package to compare two neural networks in PyTorch. There are many ways to compare two neural networks, but one robust and scalable way is using the Centered Kernel Alignment (CKA) metric, where the features of the networks are compared. Centered Kernel Alignment Centered Kernel Alignment (CKA) is a representation similarity metric that is widely used for understanding the representations learned by neural networks. Specifically, CKA takes two feature maps / representations X and Y as input and computes […]
Read more
Custom Implementation of Non-Deep Networks
Custom Implementation of Non-deep Networks arXiv:2110.07641 Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun Official Repository https://github.com/imankgoyal/NonDeepNetworks Overview: Depth is the hallmark of DNNs. But more depth means more sequential computation and higher latency. This begs the question — is it possible to build high-performing “non-deep” neural networks? We show that it is. We show, for the first time, that a network with a depth of just 12 can achieve top-1 accuracy over 80% on ImageNet, 96% on CIFAR10, and […]
Read more
Simple Pixelbot for Diablo 2 Resurrected written in python and opencv
Simple Pixelbot for Diablo 2 Resurrected written in python and opencv. Obviously only use it in offline mode as it is against the TOS of Blizzard to use it in online mode! Join the Discord Channel for help and discussions. Supported features Run Pindle, Eldtritch, Shenk Pickit with per item config. Stash picked up items (using all 4 stashes) Prebuff Revive Merc if dead Heal at Malah if needed Take potions and chicken if in trouble during fights Check for […]
Read more
Optimization and the Knapsack Problem, Decision Trees and Dynamic Programming, Graph Problems, Plotting, Stoc
This project covered these topics: Optimization and the Knapsack Problem, Decision Trees and Dynamic Programming, Graph Problems, Plotting, Stochastic Thinking, Random Walks, Inferential Statistics, Monte Carlo Simulations, Sampling and Standard Error, Experimental Data, Machine Learning, and Statistical Fallacies GitHub View Github
Read more
Python module and its web equivalent, to hide text within text by manipulating bits
cacherdutexte.github.io This project contains : Python modules (binary and decimal system 6) with a dedicated tkinter program to use it. A web version, which is actually hosted on https://cacherdutexte.github.io. I explain below how the project works, but an english version is available. See directly the English explanation 🇬🇧 🇫🇷 Comment j’ai caché du texte dans du texte C’est une façon en manipulant les bits de cacher du texte dans du texte.Imaginons la chaine de caractère : Que je veux cacher […]
Read more
A teeny Tiny module to check URLs against discord’s list of phishing domains
A teeny Tiny module to check URLs against discord’s list of phishing domains
Read more
Cleaner script to normalize knock’s output EPUBs
The excellent knock application by Benton Edmondson outputs EPUBs that seem to be DRM-free. However, if you run the application twice on the same ACSM file, the hashes do not match. This script normalizes EPUB files, and it is specifically written to normalize the output files of knock. It strips away all the differences between different EPUB files for the same book. Usage ./clean-epub.py -i input.epub -o output.epub Details In essence, it does this: Create a temporary directory, and unzip […]
Read more