Computer Vision Model Library

The Roboflow Model Library contains pre-configured model architectures for easily training computer vision models. Just add the link from your Roboflow dataset and you're ready to go! We even include the code to export to common inference formats like TFLite, ONNX, and CoreML.

If you'd like to request a model we haven't yet implemented, please get in touch.

Object Detection

YOLOv4

YOLOv4 has emerged as the best real time object detection model. YOLOv4 carries forward many of the research contributions of the YOLO family of models along with new modeling and data augmentation techniques. This implementation is in Darknet. Read More...

PyTorch Object Detection

EfficientDet

EfficientDet achieves the best performance in the fewest training epochs among object detection model architectures, making it a highly scalable architecture especially when operating with limited compute. Read More...

Tensorflow 1.5 Object Detection

Faster R-CNN

One of the most accurate object detection algorithms but requires a lot of power at inference time. A good choice if you can do processing asynchronously on a server. Read More...

Keras Object Detection

YOLO v3 Keras

Though it is no longer the most accurate object detection algorithm, YOLO v3 is still a very good choice when you need real-time detection while maintaining excellent accuracy. Keras implementation. Read More...

PyTorch Object Detection

YOLO v3 PyTorch

Though it is no longer the most accurate object detection algorithm, YOLO v3 is still a very good choice when you need real-time detection while maintaining excellent accuracy. PyTorch version. Read More...

Tensorflow 1.5 Object Detection

MobileNetSSDv2

This architecture provides good realtime results on limited compute. It's designed to run in realtime (30 frames per second) even on mobile devices. Read More...

Tensorflow 1.5 Classification

EfficientNet B2

EfficientNet is from a family of image classification models from GoogleAI that train comparatively quickly on small amounts of data, making the most of limited datasets.

Tensorflow 2 Classification

MobileNetV2 Classification

MobileNet is a GoogleAI model well-suited for on-device, real-time classification (distinct from MobileNetSSD, Single Shot Detector). This implementation leverages transfer learning from ImageNet to your dataset.

Fast.ai v2 Classification

ResNet-32

A fast, simple convolutional neural network that gets the job done for many tasks, including classification here. Read More...