YOLOv5s-seg: Semantic Segmentation
YOLOv5-Seg is an instance segmentation model in the YOLOv5 series, extending the YOLOv5 object detection architecture. Unlike standard YOLOv5, YOLOv5-Seg not only detects object locations but also generates precise segmentation masks for each detected object, enabling instance-level segmentation. This model adds a segmentation head and mask branch, incorporating convolutional layers and upsampling operations to produce high-quality segmentation results. YOLOv5-Seg retains the efficiency and real-time performance of YOLOv5, making it suitable for detailed image understanding tasks. It is widely used in applications such as autonomous driving, medical image analysis, and video surveillance, where instance segmentation is required.
Source model
- Input shape: 224x224
- Number of parameters: 7.62M
- Model size: 29.1M
- Output shape: 1x3087x117, 1x32x56x56
Source model repository: YOLOv5s-seg
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm