PyTorch Object Detection
EfficientDet is a state of the art object detection model. You will find EfficientDet useful for real time object detection.
EfficientDet has an EfficientNet backbone and a custom detection and classification network. EffcientDet is designed to efficiently scale from the smallest model size. The smallest EfficientDet, EfficientDet-D0 has 4 million weight parameters - it is truly tiny.
EfficientDet was originally released in the tensorflow and keras frameworks. EfficientDet is now available in pytorch - as we have included it here.
EfficientDet infers in 30ms in this distribution and is considered a realtime model. You can store EfficientDet with only 17 mb of storage.
EfficientDet performed state of the art on COCO when it was released. We find that EfficientDet performs slightly better than YOLOv3.
EfficientDet is an open source neural network model for the computer vision task of image detection.