Deep Learning, NLP, NMT, AI, ML
Code accompanying the paper “Wasserstein GAN” A few notes The first time running on the LSUN dataset it can take a long time (up to an hour) to create the dataloader. After the first run a small cache file will be created and the process should take a matter of seconds. The cache is a list of indices in the lmdb database (of LSUN) The only addition to the code (that we forgot, and will add, on the paper) are […]
Read more
This repo is implementation for PointNet(https://arxiv.org/abs/1612.00593) in pytorch. The model is in pointnet/model.py. It is tested with pytorch-1.0. git clone https://github.com/fxia22/pointnet.pytorch cd pointnet.pytorch pip install -e . Download and build visualization tool cd script bash build.sh #build C++ code for visualization bash download.sh #download dataset Training cd utils python train_classification.py –dataset –nepoch= –dataset_type python train_segmentation.py –dataset –nepoch= Use –feature_transform to use feature transform. Classification performance On ModelNet40: Overall Acc Original implementation 89.2 this implementation(w/o feature transform) 86.4 this implementation(w/ feature […]
Read more
This implements one of result networks from Large-scale evolution of image classifiers by Esteban Real, et. al. Requirements Training Copy two files to {torchvision_path}/models cp {__init__.py,evloution.py} {torchvision_path}/models Run python main.py -a evolution {cifar10_data_dir} cf. How to know {torchvision_path}? import torchvision print(torchvision.__file__) Note The numbers of channels are not in the paper and it is set by me similar with vgg. You need to adjust these for better performance. If you want to adsjust
Read more
Django is a powerful framework for creating web applications in Python. Its features include database models, routing URLs, authentication, user management, administrative tools, and a template language. You can compose reusable HTML that changes based on the data you pass to the template language. Django templates use tags and filters to define a mini-language that’s similar to Python—but isn’t Python. You’ll get to know Django templates through the tags and filters you use to compose reusable HTML. In this tutorial, […]
Read more
This project expands on the person-detecting doorbell system to allow it to identify faces, and announce names accordingly. Installation To install, clone this repository to your raspberry pi, descend into it, and use the following command: Architecture This project is based off the person-detecting doorbell. At its most basic it will always ring the doorbell if a person is present. When a person is present, it will check their faces against known faces. If the person is known, they will […]
Read more
This is the source code for the EMNLP 2021 (Findings) paper “Towards Improving Adversarial Training of NLP Models”. If you use the code, please cite the paper: @misc{yoo2021improving, title={Towards Improving Adversarial Training of NLP Models}, author={Jin Yong Yoo and Yanjun Qi}, year={2021}, eprint={2109.00544}, archivePrefix={arXiv}, primaryClass={cs.CL} } Prerequisites The work heavily relies on the TextAttack package. In fact, the main training code is implemented in the TextAttack package. Required packages are listed in the requirements.txt file. pip install -r requirements.txt […]
Read more
tibia bot api using python ⚙Running the app Add confidence to floor level to have more accuracy detecting user coordinates since some levels have a lot of “black” pixels. reduce/increase confidence when player bounds is not found. Add retry strategy. See also the list of contributors who participated in this project Copyright © 2020 This project is MIT licensed GitHub https://github.com/lucasmonstro/pytibia
Read more
Have your calendar appear as the wallpaper. Use at your own risk. Don’t blame me if you miss a meeting 🙂 Some parts of the scripts were bogged togather from various examples online. Please report problems using GITHUBs issue tracking system. Additionally please let me know if there are some feature requests. The scripts in this repository depend on the following programs being available: The example calendar file cal_example contains a description of the syntax togather with a couple of […]
Read more
A simple python web scraper. It gets a website and its contents and parses them with the help of bs4. Installation To install the requirements, run the following commands; To change directories: cd Dissec To make the files executable: chmod +x * To install the requirements: python requirements.py Usage Run the script using: python dissec.py It’ll prompt you, asking for a website that you want to scrape. Enter any website that you want to scrape. The website can be with […]
Read more
Learn more: https://cloud.google.com/blog/topics/developers-practitioners/push-your-code-and-see-your-builds-happening-your-terminal-git-deploy Requirements Python 3.7+ (check with python3 –version) git 1.8+ (check with git –version) A GitHub repo connected to Cloud Build with source-based deployments Installation Clone this repo Set the execution bit Copy git-deploy into a place on your PATH. # example location cp git-deploy /usr/local/bin Confirm installation by running the script: cd ~ # a non-git repo git deploy Success: fatal: not a git repository (or any of the parent directories): .git The new git extension has […]
Read more