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.

Fast.ai v2 Classification

Resnet34

Resnet34 for state of the art image classification implemented in fastai v2 and PyTorch Read More...

Tensorflow 2 Object Detection :: TFRecord

EfficientDet-D0-D7

A scalable, state of the art object detection model, implemented here within the TensorFlow 2 Object Detection API. Read More...

PyTorch Object Detection :: YOLOv5 TXT

YOLOv5

A very fast and easy to use PyTorch model that achieves state of the art (or near state of the art) results. Read More...

Darknet Object Detection :: Darknet TXT

YOLOv4-tiny

The tiny and fast version of YOLOv4 - good for training and deployment on limited compute resources, and getting a feel for your dataset Read More...

Object Detection :: Darknet TXT

YOLOv4 Darknet

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...

Keras Classification

EfficientNet

EfficientNet is a family of state of the art classification models from GoogleAI that efficiently scale up as you increase the number of parameters in the network. Read More...

PyTorch Object Detection :: COCO JSON

Detectron2

Detectron2 is model zoo of it's own for computer vision models written in PyTorch. Detectron2 includes all the models that were available in the original Detectron, such as Faster R-CNN, Mask R-CNN, RetinaNet, and DensePose. It also features several new models, including Cascade R-CNN, Panoptic FPN, and TensorMask. Read More...

PyTorch Object Detection :: COCO JSON

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 :: TFRecord

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...

PyTorch Object Detection :: Darknet TXT

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...

Keras Object Detection :: Keras TXT

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...

Tensorflow 1.5 Object Detection :: TFRecord

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...

PyTorch Object Detection :: Darknet TXT

YOLOv4 PyTorch

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 PyTorch. Read More...

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...