praateekmahajan Goto Github PK

action_recognition_ucf101

So far limited work has been done in using temporal features for feature detection, my aim is to either compare the latest state of the art tools for action recognition or to implement a vanilla solution.

algorithms_practice

Some practice questions while preparing for interviews.

cudf

cuDF - GPU DataFrame Library

deeplearning_practice

gems

Ruby gems driving Octo-matic engine. http://www.octo.ai

kubernetes-workshop

⚙️ A Gentle introduction to Kubernetes with more than just the basics. 🌟 Give it a star if you like it.

machinelearningconcepts

A list of tutorials that helped me understand certain concepts.

movie-meta-fetch

Fetch metadata of your movies easily with this script and save them in a html file to view/search for movies according to genre, awards, imdb rating.

moving-mnist-vae

Experiments to learn latent representation/physical information about moving mnist dataset.

parallel-adaboost

petastorm

Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.

predict-speed-using-dashcam

Trying to predict speed of vehicle using just dashcam (monocular) with CNN style architectures, using Optical Flow as inputs.

profiling-frameworks

pycom

Simple Flask Based ECommerce Cart System

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-transformers

👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)

spark

Apache Spark - A unified analytics engine for large-scale data processing

tempo

The purpose of this project is to provide an API for manipulating time series on top of Apache Spark. Functionality includes featurization using lagged time values, rolling statistics (mean, avg, sum, count, etc), AS OF joins, and downsampling & interpolation. This has been tested on TB-scale of historical data and is unit tested for quality purposes.

tfrecord

TFRecord reader for PyTorch

trojannn-pytorch

Implementation of https://github.com/PurduePAML/TrojanNN

vqa-2018

xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow