Ikomia HUB

Run vision-language model series based on Qwen2.5

Inference with RF-DETR models

Inference with YOLOv11 pose estimation models

Inference with YOLOv11 image classification models

Inference with YOLOv11 segmentation models

Inference with YOLOv11 models

OCR-free model for document understanding

Remove background with rembg library

Inference for Segment Anything Model 2 (SAM2).

Depth Anything V2 is a highly practical solution for robust monocular depth estimation

Instance segmentation with YOLOv9 models

Run OWLv2 a zero-shot text-conditioned object detection model

Object detection with YOLOv9 models

Depth Anything is a highly practical solution for robust monocular depth estimation

Algorithm to colorize grayscale image

Image restoration algorithms with Swin Transformer

Infer ByteTrack for object tracking

Inference of the Grounding DINO model

Inference with YOLOv8 segmentation models

Inference with YOLOv8 pose estimation models

Inference with YOLOv8 models

Face detection using the Kornia API

Multiple Object Tracking algorithm (MOT) combining a deep association metricwith the well known SORT algorithm for better performance.

Inference for pose estimation models from mmpose

Inference for MMDET from MMLAB detection models

Inference for MMLAB segmentation models

Inference for MMOCR from MMLAB KIE models

Inference for MMOCR from MMLAB text recognition models

Inference for MMOCR from MMLAB text detection models

Neural network method to paint given image in the style of the reference image.