Archive of posts with category 'Machine learning'

Training Yolo v3 model using custom dataset on Google colab

YOLO (You Only Look Once) trades some accuracy for speed. Instead of running a classifier at multiple locations and scales, YOLO applies a single neural network to the full image....

Tejashwi Kalp Taru
01 Aug 2019

Object detection with Fizyr Retinanet

One-stage detectors struggle with class imbalance: most candidate regions contain background, not objects. RetinaNet uses focal loss to address this. Easy negative samples contribute less to the loss, so training...

Tejashwi Kalp Taru
09 Jul 2019