PyTorch Object Detection

YOLO v3 PyTorch

YOLOv3 is a state of the art image detection model. You will find it useful to detect your custom objects. It is available here in Pytorch and we also have it available in Keras.

YOLOv3 inferences in roughly 30ms. YOLOv3 requires 270mb to store on your device. YOLOv3 has 65 million parameters.

YOLOv3 is a real-time object detector. Tiny-YOLOv3 can be used on Rasberry Pi. YOLOv3 is 100-1000x faster than R-CNN.

YOLO made the initial contribution of framing the object detection problem as a two step problem to first identify a bounding box (regression problem) and then identify that object's class (classification problem).

We find YOLOv3 to have slightly poorer performance than EfficientDet on an example custom dataset.

When it was released, YOLOv3 had state of the art performance on COCO relative to the models detection speed and inference time and model size.

YOLOv3 is an open source neural network model for the computer vision task of image detection.
YOLOv3 is a state of the art image detection model. You will find it useful to detect your custom objects. It is available here in Keras and we also have it available in PyTorch.

YOLOv3 inferences in roughly 30ms. YOLOv3 requires 270mb to store on your device. YOLOv3 has 65 million parameters.

YOLOv3 is a real-time object detector. Tiny-YOLOv3 can be used on Rasberry Pi.

YOLO made the initial contribution of framing the object detection problem as a two step problem to first identify a bounding box (regression problem) and then identify that object's class (classification problem).

We find YOLOv3 to have slightly poorer performance than EfficientDet on an example custom dataset.

When it was released, YOLOv3 had state of the art performance on COCO relative to the models detection speed and inference time and model size.

YOLOv3 is an open source neural network model for the computer vision task of image detection.