Browse deepinfra models:
All categories and models you can try out and directly use in deepinfra:
Category/object-detection
Object detection AI models are advanced computer vision technologies used to identify and classify objects in digital images and videos. These models use machine learning algorithms to analyze visual data and accurately detect objects, even in complex scenes. Some of the most popular object detection AI models include:
Training these models requires large datasets of annotated images, such as the COCO (Common Objects in Context) dataset, which contains over 330,000 images with annotated objects in 80 categories. Once trained, object detection AI models can be used in various applications, including video surveillance, autonomous vehicles, robotics, and more. With their ability to accurately classify and detect objects in complex scenes, object detection AI models are revolutionizing the way we analyze and interact with visual data.
object-detection
The YOLOS model, a Vision Transformer (ViT) trained using the DETR loss, achieves 42 AP on COCO validation 2017, similar to DETR and more complex frameworks like Faster R-CNN, despite its small size. The model uses a bipartite matching loss to compare predicted classes and bounding boxes to ground truth annotations. Fine-tuned on COCO 2017 object detection dataset consisting of 118k/5k annotated images for training/validation, it achieved 36.1 AP on validation set.
object-detection
The YOLOS model, a Vision Transformer (ViT) trained using the DETR loss, achieved an AP of 28.7 on COCO 2017 validation, outperforming other state-of-the-art object detection models while being much simpler. It was pre-trained on ImageNet-1k and fine-tuned on COCO 2017 object detection, a dataset consisting of 118k/5k annotated images for training/validation respectively. The model uses a bipartite matching loss and is trained using standard cross-entropy and a linear combination of the L1 and generalized IoU loss.
object-detection
We present a fine-tuned YOLOs model for license plate detection, which achieved an AP of 47.9 on the test set. Our model was trained for 200 epochs on a single GPU using Google Colab, utilizing the DETR loss and a base-sized YOLOs model. We evaluated our model on various IoU thresholds and obtained an average recall of 0.676 at IoU=0.50:0.95, with location being medium.
