Welcome to the project on Yolov4 with OpenCV for Object Detection. In this project, we will learn how to use a YOLOv4 network pretrained on the MSCOCO dataset for object detection.
Object detection has applications in various fields, from home automation to self-driving computers. YOLOv4 is one of the recent state-of-art object detection models. This project provides an overview of how to use a YOLOv4 pretrained model.
This project uses the face_recognition
library in Python to find a celebrity look-alike from a picture that you upload.
The face_recognition
library, which is built using dlib’s state-of-the-art face recognition
built with deep learning, is considered one of the simples libraries used for face recognition and manipulation. The model has an accuracy of 99.38% on the Labeled Faces in the Wild benchmark. With this library you can find faces, find and manipulate facial features, and identify faces in pictures. You can also use this library with other Python libraries to do real-time face recognition.
For more information on the face_recognition
library, you can view their official page from here.
Welcome to this project on Autoencoders for MNIST Fashion. In this project, we will understand how to implement Autoencoders using TensorFlow 2.
We will be understanding how to practically implement the autoencoder, stacking an encoder and decoder using TensorFlow 2. We will also depict the reconstructed output images by the autoencoder model.
Skills you will develop:
TensorFlow 2
scikit-learn
Matplotlib
Numpy
Welcome to the project on How to build low-latency deep-learning-based flask app. In this project, we will refactor the entire codebase of the project How to Deploy an Image Classification Model using Flask. That monolithic code will be refactored to form two microservices - the flask service and model service. The model service acts as a server that renders pretrained Tensorflow model as a deep learning API, and keeps listening for any incoming requests. The flask service requests the model service, and displays the response from the model server. This way, we write cleaner code and promote service isolation.
Further, we will introduce an engineering technique, wherein we introduce the concept of asynchrony using ZMQ networking library, in order to reduce deep learning api response time and thus make the app faster in return. By integrating ZMQ with this client-server architecture, we improve the latency of this microservice-based app. Upon completing this project, we would optimize inference time to classify the input image, and make it a low-latency web application, thus making it deployable in real-time production environments.
Blog : Improving the Performance of Deep-Learning based Flask App with ZMQ
This project depends on another project: How to Deploy an Image Classification Model using Flask
Skills you will develop: