tutorials.md

Repositories to explore

https://github.com/phlippe/uvadlc_notebooks: Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2020. https://uvadlc-notebooks.readthedocs.io/en/latest/

Quick and dirty notes (just for me)

• Attention Is All You Need Annotated version of the paper in the form of a line-by-line implementation http://nlp.seas.harvard.edu/2018/04/03/attention.html https://github.com/harvardnlp/annotated-transformer

• ViT - AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE (fully explained) https://amaarora.github.io/2021/01/18/ViT.html

• Deploy an Object-Detector Model at the Edge on AWS Panorama: https://towardsdatascience.com/deploy-an-object-detector-model-at-the-edge-on-aws-panorama-9b80ea1dd03a. More info here: https://docs.aws.amazon.com/panorama/latest/dev/panorama-welcome.html.

• Attending to Attention: A summary of a revolutionary paper “Attention is All You Need” and Implementing the Transformer using PyTorch. https://medium.com/@agniakash25/attending-to-attention-eba798f0e940

• PonderNet explained. Implementing a pondering network for the MNIST dataset. https://medium.com/@conradcardona/pondernet-explained-5e9571e657d

• Introducing Zero Shot Object Tracking: https://blog.roboflow.com/zero-shot-object-tracking/amp/

• Brain Tumor Classification with PyTorch⚡Lightning & EfficientNet 3D. https://www.kaggle.com/jirkaborovec/brain-tumor-classif-lightning-efficientnet3d

• How To Build A Computer Vision Mobile App In Flutter. https://www.digitalknights.co/blog/build-computer-vision-ios-app-in-flutter

• Data Cleaning with Python: A guide to data cleaning using the Airbnb NY data set. https://medium.com/bitgrit-data-science-publication/data-cleaning-with-python-f6bc3da64e45

• Multiclass Image Classification with Pytorch: https://github.com/MLWhiz/data_science_blogs/tree/master/compvisblog, https://towardsdatascience.com/end-to-end-pipeline-for-setting-up-multiclass-image-classification-for-data-scientists-2e051081d41c

• AutoML Tutorial: TPS (June 2021). https://www.kaggle.com/rohanrao/automl-tutorial-tps-june-2021

• Non Maximum Suppression: Theory and Implementation in PyTorch: https://learnopencv.com/non-maximum-suppression-theory-and-implementation-in-pytorch/

• Model Deployment using Flask and PyCaret: https://sagarjiyani3010.medium.com/model-deployment-using-flask-and-pycaret-b09df0a33635, https://github.com/SagarJiyani3010/House-Price-Prediction-Deployment

• A Gentle Introduction to Audio Classification With Tensorflow. https://pub.towardsai.net/a-gentle-introduction-to-audio-classification-with-tensorflow-c469cb0be6f5

• PyTorch Trainer Script + Automatic Mixed Precision using EfficientNet V2!. https://www.kaggle.com/heyytanay/pytorch-trainer-amp-efficientnetv2-kfolds

• 😷SIIM Covid-19: Box Detect & .dcm metadata. https://www.kaggle.com/andradaolteanu/siim-covid-19-box-detect-dcm-metadata

• First Steps With PySpark and Big Data Processing. https://realpython.com/pyspark-intro/

• License Plate Detection and OCR using Roboflow Inference API. https://blog.roboflow.com/license-plate-detection-and-ocr/

• Accelerating AI Modules for ROS and ROS 2 on NVIDIA Jetson Platform. https://developer.nvidia.com/blog/accelerating-ai-modules-for-ros-and-ros-2-on-jetson/?ncid=em-news-556766&mkt_tok=MTU2LU9GTi03NDIAAAF9LtuWhJI-ZuNi4bIm1SfisxgeHCoK51-PinTjEe2HWZjPfTzkBLF6k2adyj_FbhPFXL6BI9XEEOGYL1nvqLVy2InL9mfvOtVEy4-K5NpdOeaml0Ux#cid=em07_em-news_en-us

• Node Classification with Graph Neural Networks. https://keras.io/examples/graph/gnn_citations/

• PyTorchVideo: A deep learning library for video understanding. https://ai.facebook.com/blog/pytorchvideo-a-deep-learning-library-for-video-understanding/

• Video Understanding with PyTorch. https://towardsdatascience.com/video-understanding-made-simple-with-pytorch-video-and-lightning-flash-c7d65583c37e

• Using PyTorchVideo for efficient video understanding. https://towardsdatascience.com/using-pytorchvideo-for-efficient-video-understanding-24d3cd99bc3c

• 5 Steps to Training your first Video Classifier in a Flash. https://devblog.pytorchlightning.ai/5-steps-to-training-your-first-video-classifier-in-a-flash-dd11d472fded

• The Fastest Way To Build Computer Vision Applications. https://datature.io/

• Training an Instance Segmentation Model with Custom Data. https://datature.io/blog/training-an-instance-segmentation-model

• Machine learning and recommender systems using your own Spotify data. https://towardsdatascience.com/machine-learning-and-recommender-systems-using-your-own-spotify-data-4918d80632e3

• DINO: Emerging Properties in Self-Supervised Vision Transformers Summary. https://towardsdatascience.com/dino-emerging-properties-in-self-supervised-vision-transformers-summary-ab91df82cc3c

• AI Explorables: Big ideas in machine learning, simply explained. https://pair.withgoogle.com/explorables/

• Object Detection With Mask R-CNN. https://ml-showcase.paperspace.com/projects/object-detection-with-mask-r-cnn

• Data Version Control With Python and DVC. https://realpython.com/python-data-version-control/

• PyTorchVideo: A deep learning library for video understanding: https://ai.facebook.com/blog/pytorchvideo-a-deep-learning-library-for-video-understanding/

• Some examples of face & facial processing: https://github.com/MaharshSuryawala/Face-Detection-and-Facial-Expression-Recognition, https://github.com/misbah4064/drowsinessDetector/blob/master/drowsinessDetector.py

• Many examples for Deep Learning (Classification, SSD, Segmentation, Pose, face detection, face mask detection, face recognition, super resolution, age and gender estimation,...) on Raspberry Pi & Jetson Nano. https://github.com/Qengineering

• lightning-Covid19: A detector for covid-19 chest X-ray images using PyTorch Lightning (for educational purposes). https://pytorchlightning.github.io/lightning-Covid19/

• EfficientDet meets Pytorch Lightning. https://www.kaggle.com/yassinealouini/efficientdet-meets-pytorch-lightning

• Explainable AI Cheat Sheet. https://ex.pegg.io/

• Imbalanced dataset image classification with PyTorch. https://marekpaulik.medium.com/imbalanced-dataset-image-classification-with-pytorch-6de864982eb1

• Machine Learning Prediction in Real Time Using Docker and Python REST APIs with Flask. https://towardsdatascience.com/machine-learning-prediction-in-real-time-using-docker-and-python-rest-apis-with-flask-4235aa2395eb

• Supercharge Your Machine Learning Experiments with PyCaret and Gradio. https://towardsdatascience.com/supercharge-your-machine-learning-experiments-with-pycaret-and-gradio-5932c61f80d9

• 101 Data Science Interview Questions, Answers, and Key Concepts. https://online.datasciencedojo.com/blogs/101-data-science-interview-questions-answers-and-key-concepts?utm_content=165431632&utm_medium=social&utm_source=linkedin&hss_channel=lcp-3740012

• TensorRT YOLO For Custom Trained Models (Updated). https://jkjung-avt.github.io/trt-yolo-custom-updated/

  • https://jkjung-avt.github.io/trt-yolov3-custom/
  • https://github.com/jkjung-avt/tensorrt_demos
  • https://gilberttanner.com/blog/jetson-nano-yolo-object-detection

• 📚 OpenVINO Notebooks. https://github.com/openvinotoolkit/openvino_notebooks

• openvino2tensorflow. This script converts the OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC) -> TFLite (NHWC). And the conversion from .pb to saved_model and from saved_model to .pb and from .pb to .tflit… https://github.com/PINTO0309/openvino2tensorflow

• cracking-the-data-science-interview: A Collection of Cheatsheets, Books, Questions, and Portfolio For DS/ML Interview Prep. https://github.com/khanhnamle1994/cracking-the-data-science-interview

• machine-learning-systems-design. A booklet on machine learning systems design with exercises. https://github.com/chiphuyen/machine-learning-systems-design

• YOLO_v3_tutorial_from_scratch. Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch".https://github.com/ayooshkathuria/YOLO_v3_tutorial_from_scratch

  • https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/

• Deep Learning with Keras Cheat Sheet (2021), Python for Data Science. https://towardsdatascience.com/deep-learning-with-keras-cheat-sheet-2021-python-for-data-science-fba43636a9a1

• Anomaly Detection. https://medium.com/analytics-vidhya/anomaly-detection-e669ebde5cb9

• COVID19_Detection_Transfer_Learning_VGG16. https://github.com/EXJUSTICE/COVID19_Detection_Transfer_Learning_VGG16

• Pipelines: Automated machine learning with HyperParameter Tuning!. https://towardsdatascience.com/pipelines-automated-machine-learning-with-hyperparameter-tuning-part-1-b9c06a99d3c3

• Change Detection of Structures in Panchromatic Imagery. https://medium.com/geoai/change-detection-of-structures-in-panchromatic-imagery-f3286fde62e6

• An example development repository for using Nvidia Jetson Nano or Xavier as health monitor using computer vision. https://github.com/raymondlo84/nvidia-jetson-ai-monitor

• InfinityGAN: Towards Infinite-Resolution Image Synthesis. https://hubert0527.github.io/infinityGAN/

• How to Choose a CI Framework for Deep Learning: https://medium.com/pytorch-lightning/how-to-choose-a-ci-framework-for-deep-learning-d24ee9ef902c

• Data Science 101: Normalization, Standardization, and Regularization: https://www.kdnuggets.com/2021/04/data-science-101-normalization-standardization-regularization.html

• How to Combine Predictions for Ensemble Learning: https://machinelearningmastery.com/combine-predictions-for-ensemble-learning/. Also this one: https://towardsdatascience.com/ensemble-learning-bagging-boosting-3098079e5422, this one: https://machinelearningmastery.com/ensemble-machine-learning-algorithms-python-scikit-learn/, this one https://machinelearningmastery.com/weighted-average-ensemble-for-deep-learning-neural-networks/

• A Layman’s guide to ROC Curves And AUC. https://mlwhiz.com/blog/2021/02/03/roc-auc-curves-explained/?utm_campaign=a-laymans-guide-to-roc-curves-and-auc&utm_medium=social_link&utm_source=missinglettr

• Explainable AI (XAI) with a Decision Tree (Practical guide for XAI analysis with Decision Tree visualization): https://towardsdatascience.com/explainable-ai-xai-with-a-decision-tree-960d60b240bd

• Data Cleaning: Hidden Aspect of Good Data Scientist: https://dockship.io/articles/60748d13dba94b312797af1e/data-cleaning:-hidden-aspect-of-good-data-scientist

• How to Use Variance Thresholding For Robust Feature Selection: https://towardsdatascience.com/how-to-use-variance-thresholding-for-robust-feature-selection-a4503f2b5c3f

• How to Use Pairwise Correlation For Robust Feature Selection: https://towardsdatascience.com/how-to-use-pairwise-correlation-for-robust-feature-selection-20a60ef7d10

• Comprehensive data exploration with Python: https://www.kaggle.com/pmarcelino/comprehensive-data-exploration-with-python

• Plant Pathology with Lightning: https://www.kaggle.com/jirkaborovec/plant-pathology-with-lightning

• Scaled-YOLOv4: https://blog.roboflow.com/scaled-yolov4-tops-efficientdet/

• Fusing EfficientNet & YoloV5: https://towardsdatascience.com/fusing-efficientnet-yolov5-advanced-object-detection-2-stage-pipeline-tutorial-da3a77b118d1

• A journey of building an Advanced Object Detection Pipeline — Doubling YoloV5’s performance: https://towardsdatascience.com/a-journey-of-building-an-advanced-object-detection-pipeline-doubling-yolov5s-performance-b3f1559463bf

• Exploratory Data Analysis, Visualization, and Prediction Model in Python: https://towardsdatascience.com/exploratory-data-analysis-visualization-and-prediction-model-in-python-241b954e1731

• How to Choose an Activation Function for Deep Learning. https://machinelearningmastery.com/choose-an-activation-function-for-deep-learning/

• FLIR_to_Yolo. This script converts FLIR thermal dataset annotations to YOLO format. https://github.com/albertofernandezvillan/FLIR_to_Yolo

• Dimensionality reduction with Autoencoders versus PCA. https://towardsdatascience.com/dimensionality-reduction-with-autoencoders-versus-pca-f47666f80743

• P-value Explained Simply for Data Scientists: https://mlwhiz.com/blog/2019/11/11/pval/?utm_campaign=p-value-explained-simply-for-data-scientists&utm_medium=social_link&utm_source=missinglettr-linkedin