Clik here to view.
Training a custom dlib shape predictor
In this tutorial, you will learn how to train your own custom dlib shape predictor. You’ll then learn how to take your trained dlib shape predictor and use it to predict landmarks on input images and...
View ArticleClik here to view.
Tuning dlib shape predictor hyperparameters to balance speed, accuracy, and...
In this tutorial, you will learn how to optimally tune dlib’s shape predictor hyperparameters and options to obtain a shape predictor that balances speed, accuracy, and model size. Today is part two...
View ArticleClik here to view.
Label smoothing with Keras, TensorFlow, and Deep Learning
In this tutorial, you will learn two ways to implement label smoothing using Keras, TensorFlow, and Deep Learning. When training your own custom deep neural networks there are two critical questions...
View ArticleClik here to view.
Raspberry Pi and Movidius NCS Face Recognition
In this tutorial you will learn how to use the Movidius NCS to speedup face detection and face recognition on the Raspberry Pi by over 243%! If you’ve ever tried to perform deep learning-based face...
View ArticleClik here to view.
Optimizing dlib shape predictor accuracy with find_min_global
In this tutorial you will learn how to use dlib’s find_min_global function to optimize the options and hyperparameters to dlib’s shape predictor, yielding a more accurate model. A few weeks ago I...
View ArticleClik here to view.
Intro to anomaly detection with OpenCV, Computer Vision, and scikit-learn
In this tutorial, you will learn how to perform anomaly/novelty detection in image datasets using OpenCV, Computer Vision, and the scikit-learn machine learning library. Imagine this — you’re fresh...
View ArticleClik here to view.
YOLO and Tiny-YOLO object detection on the Raspberry Pi and Movidius NCS
In this tutorial, you will learn how to utilize YOLO and Tiny-YOLO for near real-time object detection on the Raspberry Pi with a Movidius NCS. The YOLO object detector is often cited as being one of...
View ArticleClik here to view.
How to use OpenCV’s “dnn” module with NVIDIA GPUs, CUDA, and cuDNN
In this tutorial, you will learn how to use OpenCV’s “Deep Neural Network” (DNN) module with NVIDIA GPUs, CUDA, and cuDNN for 211-1549% faster inference. Back in August 2017, I published my first...
View ArticleClik here to view.
OpenCV ‘dnn’ with NVIDIA GPUs: 1549% faster YOLO, SSD, and Mask R-CNN
In this tutorial, you’ll learn how to use OpenCV’s “dnn” module with an NVIDIA GPU for up to 1,549% faster object detection (YOLO and SSD) and instance segmentation (Mask R-CNN). Last week, we...
View ArticleClik here to view.
Autoencoders with Keras, TensorFlow, and Deep Learning
In this tutorial, you will learn how to implement and train autoencoders using Keras, TensorFlow, and Deep Learning. Today’s tutorial kicks off a three-part series on the applications of autoencoders:...
View ArticleClik here to view.
Denoising autoencoders with Keras, TensorFlow, and Deep Learning
In this tutorial, you will learn how to use autoencoders to denoise images using Keras, TensorFlow, and Deep Learning. Today’s tutorial is part two in our three-part series on the applications of...
View ArticleClik here to view.
Anomaly detection with Keras, TensorFlow, and Deep Learning
In this tutorial, you will learn how to perform anomaly and outlier detection using autoencoders, Keras, and TensorFlow. Back in January, I showed you how to use standard machine learning models to...
View ArticleClik here to view.
NVIDIA Jetson Nano .img pre-configured for Deep Learning and Computer Vision
In this tutorial you will learn how to use my pre-configured NVIDIA Jetson Nano .img for Computer Vision and Deep Learning. This .img includes TensorFlow, Keras, TensorRT, OpenCV, etc. pre-installed!...
View ArticleClik here to view.
Grad-CAM: Visualize class activation maps with Keras, TensorFlow, and Deep...
In this tutorial, you will learn how to visualize class activation maps for debugging deep neural networks using an algorithm called Grad-CAM. We’ll then implement Grad-CAM using Keras and TensorFlow....
View ArticleClik here to view.
Detecting COVID-19 in X-ray images with Keras, TensorFlow, and Deep Learning
In this tutorial, you will learn how to automatically detect COVID-19 in a hand-created X-ray image dataset using Keras, TensorFlow, and Deep Learning. Like most people in the world right now, I’m...
View ArticleI want to help you the best I can during COVID-19
Many PyImageSearch readers (myself included) are quarantined or displaced from their work, school, or research lab due to COVID-19. I understand this is a terrible time for everyone and I want to help...
View ArticleClik here to view.
Using TensorFlow and GradientTape to train a Keras model
In this tutorial, you will learn how to use TensorFlow’s GradientTape function to create custom training loops to train Keras models. Today’s tutorial was inspired by a question I received by...
View ArticleClik here to view.
How to configure your NVIDIA Jetson Nano for Computer Vision and Deep Learning
In today’s tutorial, you will learn how to configure your NVIDIA Jetson Nano for Computer Vision and Deep Learning with TensorFlow, Keras, TensorRT, and OpenCV. Two weeks ago, we discussed how to use...
View ArticleClik here to view.
Autoencoders for Content-based Image Retrieval with Keras and TensorFlow
In this tutorial, you will learn how to use convolutional autoencoders to create a Content-based Image Retrieval system (i.e., image search engine) using Keras and TensorFlow. A few weeks ago, I...
View ArticleClik here to view.
An interview with Yi Shern, Machine Learning Engineer at 123RF R&D
In today’s blog post, I interview Yi Shern, a PyImageSearch reader and Machine Learning Engineer at 123RF.com, a popular stock photo website. If you’re unfamiliar with the term, a “stock photo” is a...
View Article