Author: Deep Learner
Unofficial API wrapper for seedr.cc
Unofficial API wrapper for seedr.cc Inspired by theabbie‘s seedr-api Powered by @harp_tech (Telegram) How to use
Read more
Facilitates implementing deep neural-network backbones, data augmentations
facilitates implementing deep neural-network backbones, data augmentations, optimizers and learning schedulers. backbones loss functions augumentation styles optimizers schedulers data types visualizations Refer to docs/installation.md for installion of general_backbone package. Model backone Currently, general_backbone supports more than 70 type of resnet models such as: resnet18, resnet34, resnet50, resnet101, resnet152, resnext50. All models is supported can be found in general_backbone.list_models() function: import general_backbone general_backbone.list_models() Results {‘resnet’: [‘resnet18’, ‘resnet18d’, ‘resnet34’, ‘resnet34d’, ‘resnet26’, ‘resnet26d’, ‘resnet26t’, ‘resnet50’, ‘resnet50d’, ‘resnet50t’, ‘resnet101’, ‘resnet101d’, ‘resnet152’, ‘resnet152d’, ‘resnet200’, ‘resnet200d’, […]
Read more
HiddenMarkovModel implements hidden Markov models with Gaussian mixtures as distributions on top of TensorFlow
HiddenMarkovModel implements hidden Markov models with Gaussian mixtures asdistributions on top of TensorFlow 2.0 Installation pip install –upgrade git+https://gitlab.com/kesmarag/hmm-gmm-tf2 HiddenMarkovModel(p0, tp, em_w, em_mu, em_var)
Read more
A Telegram Bot that can download music from Spotify
A Telegram Bot that can download music from Spotify RevSpotify is a fast, useful telegram bot to have Spotify music on Telegram. ✨ Features ( till now ) Download tracks from Spotify Download album from Spotify Download playlist from Spotify Download artist’s top tracks from Spotify ⚙️ Installation RevSpotify only and only requires Docker to run. Install Docker and start the bot, docker takes care of other dependencies. Now clone the repo: git clone https://github.com/revisto/RevSpotify cd RevSpotify Let’s take care […]
Read more
A Street Fighter game in Pygame
Street Fighter, commonly abbreviated as SF or スト, is a Japanese competitive fighting video game franchise developed and published by Capcom According to Wikipedia, I tried to create a bad clone of it using pygame 😂. Here is a glimpse of it Space.Fighter.2021-10-22.18-05-54.mp4 Installation Use the package manager pip to install pygame. Contributing Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change. Please make sure to update tests as […]
Read more
Django Templates: Built-in Tags and Filters
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
A sorting visualizer made with Tkinter
This is a sorting visualizer made with Tkinter. Make sure you’ve installed tkinter in your system to use this visualizer To install tkinter using python package manager, run the following: pip install tk Or follow the below website https://www.tutorialspoint.com/how-to-install-tkinter-in-python The visualizer has: Merge Sort Selection Sort Bubble Sort Insertion Sort Various colours are used to make the visualizer easily understandable. Updates are highly appreciatable GitHub View Github
Read more
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
Andreas Fürst* 1,Elisabeth Rumetshofer* 1,Viet Tran1,Hubert Ramsauer1,Fei Tang3,Johannes Lehner1,David Kreil2,Michael Kopp2,Günter Klambauer1,Angela Bitto-Nemling1,Sepp Hochreiter1 2 1 ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria2 Institute of Advanced Research in Artificial Intelligence (IARAI)3 HERE Technologies* Equal contribution Detailed blog post on this paper at this link. The full paper is available here. This repository contains the implemenation of CLOOB used to obtain the results reported in the paper.The implementation is based on OpenCLIP, […]
Read more
Self-Supervised Learning by Estimating Twin Class Distribution
Codes and pretrained models for TWIST: @article{wang2021self, title={Self-Supervised Learning by Estimating Twin Class Distributions}, author={Wang, Feng and Kong, Tao and Zhang, Rufeng and Liu, Huaping and Li, Hang}, journal={arXiv preprint arXiv:2110.07402}, year={2021} } TWIST is a novel self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to produce twin class distributions of two augmented images. Without supervision, we enforce the class distributions of different augmentations to […]
Read more