Trending Posts

Object detection on images using pretrained models from tensorflow model zoo and draw results on output images.

AzureML is a machine learning cloud-based service from Azure cloud used for development, training and deployment of Machine Learning models and solutions

Use Azure Cognitive face service to detect faces in images and also match faces to recognize person in images. We can also use it to group faces and face recognition.

Use Moviepy to split audio from a video files, perform different operation and export to a audio file.

Train a Deep learning image classification model with no or very less code and serve using an endpoint using azure cognitive services.

Perform Optical character recognition for 80+ languages using easy ocr easily in python and using different libraries.

Optimize tensorflow deep learning models using TensorRT by nvidia to speed up inference of models with good accuracy.

For any model, we train for a specific purpose, we need to deploy it on some cloud or local device to use it for new data, so here we will learn about cloud deployment as API

Pose estimation using mediapipe in images and videos with person segmantation and draw landmarks on images or apply person segmentation using python

Use Yolov5 architecture to train model with pytorch backend for different dataset and convert dataset from one format to other for training of yolov5 object detection models.

Face Detection and Recognition is a very used part in Deep Learning. We use face detection and recognition for different tasks like login on applications, person recognition and different attendence systems.

With PaddleOCR, performing OCR in Python has become easier than ever. Learn to easily detect and recognize text from images with PaddleOCR.

Read video frome files, webcam or stream and process video using opencv python and finally write video back to a file using opencv writer.

Face and basic landmarks detection using mediapipe models with efficiency and very good accuracy and draw on image or save detected faces using opencv in python.

Image classification is a very basic example in computer vision yet used widely for a lot of tasks. In image classification, we can input and image to deep learning model and get related label for class which image belongs to. We can use image classification for classifying an object from different classes, checking quality of a manufactured objects(good or not),

Semantic Segmentation using pretrained transformer segformer models usign Pytorch in python and using models with different parameters and input shapes.

Hand Landmark detection using mediapipe to get 21 landmarks for each hand, hand handedness and bbox coordinates with lower latency and high accuracy and process on images and videos.

Tesseract is a open-source OCR engine owened by Google for performing OCR operations on different kind of images. Use pytesseract to process different type of images and localize text location with confidence.

Create deep learning models application using flask as web service and deploy to google cloud run using docker and continuous deployment using Github.