Build a model which will take keywords as inputs and generate sentences as outputs

keytotext Idea is to build a model which will take keywords as inputs and generate sentences as outputs. Model: Keytotext is based on the Amazing T5 Model: k2t: Model k2t-tiny: Model k2t-base: Model mrm8488/t5-base-finetuned-common_gen (by Manuel Romero): Model Training Notebooks can be found in the Training Notebooks Folder Note: To add your own model to keytotext Please read Models Documentation Usage: Example usage: Example Notebooks can be found in the Notebooks Folder pip install keytotext UI: UI: pip install streamlit-tags […]

Read more

PyTorch implementation of various fundamental RL algorithms

Reinforcement Learning (PyTorch) This repo will contain PyTorch implementation of various fundamental RL algorithms. It’s aimed at making it easy to start playing and learning about RL. The problem I came across investigating other DQN projects is that they either: Don’t have any evidence that they’ve actually achieved the published results Don’t have a “smart” replay buffer (i.e. they allocate (1M, 4, 84, 84) ~ 28 GBs! instead of (1M, 84, 84) ~ 7 GB) Lack of visualizations and debugging […]

Read more

Machine Translation Weekly 79: More context in MT

The lack of broader context is one of the main problems in machine translation and in NLP in general. People tried various methods with actually quite mixed results. A recent preprint from Unbabel introduces an unusual quantification of context-awareness and based on that do some training improvements. The title of the paper is Measuring and Increasing Context Usage in Context-Aware Machine Translation and will be presented at ACL 2021. The paper measures how well informed the model is about the […]

Read more

A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation

CFPNet-M This repository contains the implementation of a novel light-weight real-time network (CFPNet-Medicine: CFPNet-M) to segment different types of biomedical images. It is a medical version of CFPNet, and the dataset we used from top to bottom are DRIVE, ISBI-2012, Infrared Breast, CVC-ClinicDB and ISIC 2018. The details of CFPNet-M and CFPNet can be found here respectively. Architecture of CFPNet-M CFP module CFPNet-M Dataset In this project, we test five datasets: [x] Infrared Breast Dataset [x] Endoscopy (CVC-ClinicDB) [x] Electron […]

Read more

An all MLP solution to image classification in Pytorch

ResMLP – Pytorch Implementation of ResMLP, an all MLP solution to image classification out of Facebook AI, in Pytorch Install $ pip install res-mlp-pytorch Usage import torch from res_mlp_pytorch import ResMLP model = ResMLP( image_size = 256, patch_size = 16, dim = 512, depth = 12, num_classes = 1000 ) img = torch.randn(1, 3, 256, 256) pred = model(img) # (1, 1000) Citations @misc{touvron2021resmlp, title = {ResMLP: Feedforward networks for image classification with data-efficient training}, author = {Hugo Touvron and […]

Read more

TensorFlow implementation of Barlow Twins

Barlow-Twins-TF This repository iimplements Barlow Twins (Barlow Twins: Self-Supervised Learning via Redundancy Reduction) in TensorFlow and demonstrates it on the CIFAR10 dataset. Summary: With a ResNet20 as a trunk and a 3-layer MLP (each layer containing 2048 units) and 100 epochs of pre-training, this training notebook can give 62.61% accuracy on the CIFAR10 test set. The pre-training total takes ~23 minutes on a single Tesla V100. There are minor differences from the original implementation. However, the original loss function and […]

Read more

Self-Supervised Contrastive Learning of Music Spectrograms

Self-Supervised Music Analysis Self-Supervised Contrastive Learning of Music Spectrograms. Dataset Songs on the Billboard Year End Hot 100 were collected from the years 1960-2020. This list tracks the top songs of the US market for a given calendar year based on aggregating metrics including streaming plays, physical and digital purchases, radio plays, etc. In total the dataset includes 5737 songs, excluding some songs which could not be found and some which are duplicates across multiple years. It’s worth noting that […]

Read more

A python library to convert arbitrary strings representing business opening hours into a JSON format

Python Opening Hours parser a python library to convert arbitrary strings representing business opening hours into a JSON format that’s easier to use in code This library parses opening hours from various human-readable strings such as “Mon- Fri 9:00am – 5:30pm” into a more standard JSON format that can be processed more easily. The format opening_hours = [ { “day”: “monday”, “opens”: “9:00”, “closes”: “17:00” }, //.. ] Installation pip install jsonify-opening-hours Usage The simplest example is just printing the […]

Read more

A bot that posts a Hadith every hour on Twitter & Facebook with python

Hadith Every Hour A bot that posts a Hadith every hour on Twitter & Facebook. (Every 3 hours for now to avoid spamming) Status Currently posting the Hadiths from Sahih al-Bukhari in serial. Concept It’s really simple. GitHub action is written in this file. You can notice a scheduler – on: schedule: – cron: “0 */3 * * *” And the rest of the process is self explanatory. A tracker is used to put the latest posted Hadith number in […]

Read more

A python script for Homeassistant that counts down the days to birthdays

Date Countdown A python script for Homeassistant that counts down the days to birthdays, anniversaries etc Important note I no longer use homeassistant so if this script stops being compatible with homeassistant that will be the end of the line. That said, it hasn’t needed any maintenence in over a year and was working well so it will probably be fine to use for a long while yet. How it works This script creates a sensor that a counts down […]

Read more
1 630 631 632 633 634 912