Azure Custom Vision Alternatives

Azure Custom Vision lets you train fine-tuned models to identify specific objects. Below are alternatives to Azure Custom Vision that enable you to train your own vision model.

All models listed below can be deployed on the edge (i.e. on NVIDIA Jetson or Raspberry Pi) or using a hosted, scalable API.
‍
If you're more interested in deploying a model without code, check out our Roboflow Deploy product.

Classification

Classification

Classification

Classification

Model Size:

MB

Parameters:

428000000.0

Architecture:

CLIP (Contrastive Language-Image Pre-Training) is an impressive multimodal zero-shot image classifier that achieves impressive results in a wide range of domains with no fine-tuning. It applies the recent advancements in large-scale transformers like GPT-3 to the vision arena. Learn more »

Deploy on the edge and at scale with Roboflow Inference

Run model on videos with Roboflow Hosted Video Inference

Jupyter notebook

Object Detection

Object Detection

Object Detection

Object Detection

Model Size:

68200000.0

MB

Parameters:

Architecture:

YOLO, CNN

YOLOv8 is a state-of-the-art object detection and image segmentation model created by Ultralytics, the developers of YOLOv5. Learn more »

Deploy on the edge and at scale with Roboflow Inference

Run model on videos with Roboflow Hosted Video Inference

Jupyter notebook

Object Detection

Object Detection

Object Detection

Object Detection

Model Size:

MB

Parameters:

Architecture:

DocTR is an Optical Character Recognition tool powered by deep learning. Learn more »

Deploy on the edge and at scale with Roboflow Inference

Run model on videos with Roboflow Hosted Video Inference

Jupyter notebook

Multimodal Model

Multimodal Model

Multimodal Model

Multimodal Model

Model Size:

4000000000.0

MB

Parameters:

3 Billion

Architecture:

PaliGemma is a vision language model (VLM) by Google that has multimodal capabilities. Learn more »

Deploy on the edge and at scale with Roboflow Inference

Run model on videos with Roboflow Hosted Video Inference

Jupyter notebook

Multimodal Model

Multimodal Model

Multimodal Model

Multimodal Model

Model Size:

MB

Parameters:

Architecture:

Gemini is a family of Large Multimodal Models (LMMs) developed by Google Deepmind focused specifically on multimodality. Learn more »

Deploy on the edge and at scale with Roboflow Inference

Run model on videos with Roboflow Hosted Video Inference

Jupyter notebook

Deploy a computer vision model today

Join 800,000+ developers curating high quality datasets and deploying better models with Roboflow.