YOLOv8-Segmentation: Semantic Segmentation
YOLOv8-Segmentation is one of the latest versions of the YOLO series, focusing on object detection and instance segmentation tasks. It combines YOLOv8's efficient object detection capabilities with instance segmentation, allowing for precise object boundary localization and segmentation within images. Compared to previous YOLO versions, YOLOv8-Seg features architectural improvements that enhance accuracy and speed for segmentation tasks. The model incorporates advanced convolutional neural network designs, with deeper feature extraction networks and efficient inference mechanisms, making it highly effective in real-time segmentation tasks. YOLOv8-Seg is widely used in applications like autonomous driving, medical image analysis, and video surveillance, offering a powerful solution for instance segmentation.
Source model
- Input shape: 640x640
- Number of parameters: 11.27M
- Model size: 45.22M
- Output shape: 1x32x160x160, 1x116x8400
Source model repository: YOLOv8-Seg
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm