Author: Deep Learner

Machine Learning

A repository of PyBullet utility functions for robotic motion planning

pybullet-planning (ss-pybullet) A repository of PyBullet utility functions for robotic motion planning, manipulation planning, and task and motion planning (TAMP). This repository was originally developed for the PDDLStream (previously named STRIPStream) approach to TAMP. With the help of Yijiang Huang, a stable and documented fork of ss-pybullet named pybullet_planning is available through PyPI. However, new features will continue to be introduced first through ss-pybullet. Installation Install PyBullet on OS X or Linux using: $ pip install numpy pybullet $ git […]

Read more
Advanced, NLP, Project, Python, Structured Data, Supervised, Technique, Text

A Guide to Feature Engineering in NLP

Overview Feature engineering in NLP is understanding the context of the text. In this blog, we will look at some of the common feature engineering in NLP. We will compare the results of a classification task with and without doing feature engineering   Table of Content Introduction NLP task overview List of features with code Implementation Results comparison with and without doing feature engineering Conclusion Introduction   “If 80 percent of our work is data preparation, then ensuring data quality […]

Read more
denoising parallel corpora, NLP

Issue #126 – Learning Feature Weights for Denoising Parallel Corpora

15 Apr21 Issue #126 – Learning Feature Weights for Denoising Parallel Corpora Author: Dr. Patrik Lambert, Senior Machine Translation Scientist @ Iconic Introduction Large web-crawled parallel corpora constitute a very useful source of data to improve neural machine translation (NMT) engines. However, their effectiveness is reduced by the large amount of noise they usually contain. As early as in issue #2 of this series, we pointed out that NMT is particularly sensitive to noise in the training data. In issue […]

Read more
Search

Pixel Art Reverse Image Search for OpenGameArt

PixelArtSearch Pixel art search engine for opengameart. ## What data do you need on each image to create a reverse image search? I used [VGG16 feature extraction](https://towardsdatascience.com/extract-features-visualize-filters-and-feature-maps-in-vgg16-and-vgg19-cnn-models-d2da6333edd0) in [my script for this](https://github.com/emnh/PixelArtSearch/blob/master/scripts/featureVectors.py). See the article for more information, but in essence it’s 4096 32-bit floating point numbers for each image, which describe various features of the image, say for instance in a very simplified way how many stripes or squares it has or how green it is. But these features […]

Read more
Natural Language Processing

Transfer learning for NLP models by annotating your textual data

Label Studio for Transformers Transfer learning for NLP models by annotating your textual data without any additional coding. This package provides a ready-to-use container that links together: Quick Usage Install Label Studio and other dependencies pip install -r requirements.txt Create ML backend with BERT classifier label-studio-ml init my-ml-backend –script models/bert_classifier.py cp models/utils.py my-ml-backend/utils.py Create ML backend with BERT named entity recognizer label-studio-ml init my-ml-backend –script models/ner.py cp models/utils.py my-ml-backend/utils.py Start ML backend at http://localhost:9090 label-studio-ml start my-ml-backend Start Label Studio […]

Read more
Images

OpenAI DALLE model and generating images from given texts

DALLE-reproduction This repository is for sharing pre-trained OpenAI DALLE model and generating images from given texts. All models are trained by lucidrains/DALLE-pytorch + VQGAN (Taming transformer) with different training code and BPE model. The notebook includes Text to image generation Pre-trained CLIP reranking 3. Generate rest of image based on the given cropped image Usage Install requirements $ pip install -r requirements Install DeepSpeed Follow the instruction here and install DeepSpeed Models Download models below and save them in pretrained […]

Read more
Machine Learning

A Legate library that aims to provide a distributed and accelerated drop-in replacement

Legate NumPy Legate NumPy is a Legate library that aims to provide a distributed and accelerated drop-in replacement for the NumPy API on top of the Legion runtime. Using Legate NumPy you do things like run the final example of the Python CFD course completely unmodified on 2048 A100 GPUs in a DGX SuperPOD and achieve good weak scaling. Legate NumPy works best for programs that have very large arrays of data that cannot fit in the memory of a […]

Read more
Images

A subfield of machine learning focused on developing representations of images

Curator Self-supervised learning is a subfield of machine learning focused on developing representations of images without any labels, which is useful for reverse image searching, categorization and filtering of images, especially so when it would be infeasible to have a human manually inspect each individual image. It also has downstream benefits for classification tasks. For instance, training SSL on 100% of your data and finetuning the encoder on the 5% of data that has been labeled significantly outperforms training a […]

Read more
Machine Learning

Implementation of different architectures for emotion recognition in conversations

Emotion Recognition in Conversations Unlike other emotion detection models, these techniques consider the party-states and inter-party dependencies for modeling conversational context relevant to emotion recognition. The primary purpose of all these techniques are to pretrain an emotion detection model for empathetic dialogue generation. Interaction among different controlling variables during a dyadic conversation between persons X and Y. Grey and white circles represent hidden and observed variables, respectively. P represents personality, U represents utterance, S represents interlocutor state, I represents interlocutor […]

Read more
Machine Learning

2D fluid simulation implementation of Jos Stam paper on real-time fuild dynamics

Fluid Simulation 2D fluid simulation implementation of Jos Stam paper on real-time fuild dynamics, including some suggested extensions. Usage Download this repo and store it in your computer. Open a terminal and go to the root directory of this folder. Make sure you have installed the needed dependencies by typing: $ pip install numpy $ pip install matplotlib $ pip install ffmpeg Note: Go to Install FFmpeg on Windows section if you haven’t installed FFmpeg software locally before. It must […]

Read more
1 … 707 708 709 710 711 … 973