I am excited to share that we are publicly releasing a new state-of-the-art pretrained ResNet-50 model, measured by the mean average score across seven popular computer vision benchmarks.
I see no link posts are allowed, so I’m not 100% sure how to share this with you. If you are interested in learning more about the techniques we used or downloading the model, you can do so by visiting: https://www.microsoft.com/en-us/research/blog/microsoft-vision-model-resnet-50-combines-web-scale-data-and-multi-task-learning-to-achieve-state-of-the-art/
We will also host a webinar on February 25th to walk people through how to use the pretrained vision model to build an example image classifier, then have a live QnA where we answer your questions. Join us if you can!