covid19-dashboard - A site that displays up to date COVID-19 stats, powered by fastpages.

•    Jupyter

---

This project showcases how you can use fastpages to create a static dashboard that update regularly using Jupyter Notebooks. Using fastpages, data professionals can share dashboards (that are updated with new data automatically) without requiring any expertise in front end development. The content of this site shows statistics and reports regarding Covid-19.

github-pages data-science jupyter analytics nteract data-visualisation matplotlib pymc3 fastai altair papermill github-actions covid-19 covid19 covid-data fastpages

duckgoose - Utils for fast.ai course

•    Python

---

Utility scripts for the online fast.ai course. There are two main parts: one to download and organise arbitrary image classes, and one to highlight what parts of an image is activating the decision for a classification. Here is a full example of creating a class activation maps for ducks and geese using fast ai.

fastai deep-learning image-classification

quick-nlp - Pytorch NLP library based on FastAI

•    Python

---

Installation of fast.ai library is required. Please install using the instructions here . It is important that the latest version of fast.ai is used and not the pip version which is not up to date. The main goal of quick-nlp is to provided the easy interface of the fast.ai library for seq2seq models.

pytorch fastai nlp-library seq2seq

fastai-docker - Fast.AI course complete docker container for Paperspace and Gradient

•    Dockerfile

---

This repos containers dockerfiles for use with Fast.ai online courses. Each folder corresponds with the verion of the Fast.ai course you are participating in. Course version specific readme files are provided within each subdirectory.

paperspace gradient fastai machine-learning deep-learning pytorch

code_search - Code For Medium Article: "How To Create Natural Language Semantic Search for Arbitrary Objects With Deep Learning"

•    Jupyter

---

You can use these container to reproduce the environment the authors used for this tutorial. Incase it is helpful, I have provided a requirements.txt file, however, we highly recommend using the docker containers provided below as the dependencies can be complicated to build yourself. hamelsmu/ml-gpu: Use this container for any gpu bound parts of the tutorial. We recommend running the entire tutorial on an aws p3.8xlarge and using this image.

machine-learning nlp deep-learning tensorflow keras pytorch fastai search-algorithm semantic-search semantic-search-engine search searching-algorithms tutorial data-science natural-language-processing machine-learning-on-source-code ml-on-code code-search

raster-vision-fastai-plugin - PyTorch/fastai backend plugin for Raster Vision

•    Python

---

This plugin uses PyTorch and fastai to implement a semantic segmentation backend plugin for Raster Vision. ⚠️ This repo is deprecated, as Raster Vision 0.10 has built-in PyTorch backends. However, it still may be useful as an example of how to construct a backend plugin.

pytorch fastai

Benchmarking-and-MLI-experiments-on-the-Adult-dataset - Contains benchmarking and interpretability experiments on the Adult dataset using several libraries

•    Jupyter

---

The initial experiments were a part of an assignment given from TCS ILP Innovations' Lab. Later as my appetite for the wonderful field of machine learning increased, I decided to give it another try and try out the new libraries. It includes benchmarking and interpretability experiments on the Adult Data set using libraries like fastai, h2o and interpret. Along with these, I have shown how one can use the interpret library to construct explanations for sklearn models. Note that keras models can be converted to sklearn variants and this enables interpret to work equally on these models as well.

data-science machine-learning tensorflow fastai h2oai interpretable-machine-learning microsoft-interpret

Breast-Cancer-Detection-using-Deep-Learning - Experiments to show the usage of deep learning to detect breast cancer from breast histopathology images

•    Jupyter

---

Invasive Ductal Carcinoma (IDC) is the most common subtype of all breast cancers. To assign an aggressiveness grade to a whole mount sample, pathologists typically focus on the regions which contain the IDC. As a result, one of the common pre-processing steps for automatic aggressiveness grading is to delineate the exact regions of IDC inside of a whole mount slide. The original dataset consisted of 162 whole mount slide images of Breast Cancer (BCa) specimens scanned at 40x. From that, 277,524 patches of size 50 x 50 were extracted (198,738 IDC negative and 78,786 IDC positive). Each patch’s file name is of the format: u_xX_yY_classC.png — > example 10253_idx5_x1351_y1101_class0.png . Where u is the patient ID (10253_idx5), X is the x-coordinate of where this patch was cropped from, Y is the y-coordinate of where this patch was cropped from, and C indicates the class where 0 is non-IDC and 1 is IDC.

computer-vision deep-learning medical-imaging class-imbalance fastai resnet50

Malaria-Detection-with-Deep-Learning - Deep learning based solution to automatically analyze medical images for malaria testing

•    Jupyter

---

The motivation of this notebook comes from a PyImageSearch tutorial Deep Learning and Medical Image Analysis with Keras. In that tutorial, Adrian Rosebrock of PyImageSearch briefed about medical tests condicted for testing malaria and how he was able to achieve SOTA score over the work as discussed in Pre-trained convolutional neural networks as feature extractors toward improved parasite detection in thin blood smear images by Rajaraman et al. Adrian's model was able to yield an accuracy score of 97% with a training time of about 54 minutes on Titan X GPU, whereas the model discussed in the paper took almost a day to train and generated an accuracy score of 95.9%. So, I decided to challenge myself to see if I could apply the modern deep learning practices (as taught by Jeremy Howard in the course Practical Deep Learning for Coders v3) with the help of the fastai library. The good news is I did.

computer-vision deep-learning medical-imaging fastai resnet-34

Parkinson-s-Disease-Classifier - Deep learning experiments to design a model to predict Parkinson's diseases with the images of Spiral/Wave test

•    Jupyter

---

Adrian Rosebrock of PyImageSearch recently released a brand new tutorial: Detecting Parkinson’s Disease with OpenCV, Computer Vision, and the Spiral/Wave Test which shows how to automatically detect Parkinson’s disease in hand-drawn images of spirals and waves. Adrian used classical computer vision techniques like Histogram of Oriented Gradients (HOG) for quantifying the features of the images and used them to train a Random Forest Classifier. He got an accuracy of 83.33%. I decided to apply deep learning to this problem and see if I can push the score. To see if I was able to do this, I would request you to take a look at the accompanying notebook here.

computer-vision deep-learning fastai resnet-34

code-intelligence - ML-Powered Developer Tools, using Kubeflow

•    Jupyter

---

One of the promises of machine learning is to automate mundane tasks and augment our capabilities, making us all more productive. However, one domain that doesn’t get much attention that is ripe for more automation is the domain of software development itself. This repository contains projects that are live machine learning-powered devloper tools, usually in the form of GitHub apps, plugins or APIs. We build these tools with the help of Kubeflow, in order to dog-food tools that Kubeflow developers themselves will benefit from, but also to surface real-world examples of end-to-end machine learning applications built with Kubeflow.

nlp kubernetes flask machine-learning natural-language-processing deep-learning rest-api pytorch fastai kubeflow

coronavirus-mask-image-dataset - Image dataset from Instagram of people wearing medical masks, no mask, or a non-medical (DIY) mask

•    Jupyter

---

Note: This dataset links to images on Instagram. We do not store or own the images on Instagram. Image dataset from Instagram of people wearing medical masks, non-medical (DIY) masks, or no mask. Created using the Universal Data Tool for helping people come up with creative solutions for COVID-19 problems. The dataset currently has roughly ~1,205 image samples.

machine-learning computer-vision images dataset fastai coronavirus covid-19 covid19

autofocus - Deep learning computer vision for classifying wildlife in camera trap images

•    Jupyter

---

This project uses deep learning computer vision to label images taken by motion-activated "camera traps" according to the animals they contain. Accurate models for this labeling task can address a major bottleneck for wildlife conservation efforts. If you just want to get labels for your images, you can use the following steps to run a service that passes images through a trained model.

computer-vision deep-learning pytorch camera-traps fastai conservation-bio