PyTorch
You can scarcely find a good article on deploying computer vision systems in industrial scenarios. So, we decided to write a blog post series on the topic. The topics we
This blog post covers object detection training of the YOLOv5 model on a custom dataset using the small and medium YOLOv5 models.
Intersection Over Union (IoU) is a number that quantifies degree of overlap between two boxes. In object detection and segmentation, it is a helper metric for evaluating models. Continue reading
Moving away from traditional document scanners, learn how to create a Deep Learning-based Document Segmentation model using DeepLabv3 architecture in PyTorch.
Explaining and understanding the inner workings of FairMOT Tracker. Checkout the intermediate outputs, and compare the results with DeepSort Tracker
FCOS: Fully Convolutional One-stage Object Detection is an anchor-free (anchorless) object detector. Inference on image and video with PyTorch.