Skip to content
ModelListedExternal
Browse files

Ocean Yolo

Specialized YOLOv5 detection models for fine-grained localization and classification of marine targets. Invoked after the routing stage. | File | Task | Classes | Architecture | | sonardetector/best.pt | Sonar target...

KindOtherVersionRevision a3719c6

Model source

Kind
Other
File size
8.10–13.9 MB
Version
vRevision a3719c6
Updated
Sep 27, 2026
Downloads
0
Tasks
Object detection
Source
Hugging Face

Source description

Ocean-yolo: Marine Object Detectors

Specialized YOLOv5 detection models for fine-grained localization and classification of marine targets. Invoked after the routing stage.

Model Weights

FileTaskClassesArchitecture
sonar_detector/best.ptSonar target detection15 sonar categoriesYOLOv5
fish_detector/best.ptFish species/object detectionMultiple fish classesYOLOv5
coral_detector/best.ptCoral species/object detectionMultiple coral classesYOLOv5

Usage

Requires YOLOv5.

import torch
# Load detector (e.g., Fish)
model = torch.hub.load("ultralytics/yolov5", "custom", path="fish_detector/best.pt", force_reload=True)
# Inference
results = model("input.jpg", conf=0.5, iou=0.45)
results.print()

Sources

1 source
Hugging FacePrimaryVersion a3719c609eeaf60251cd4c8e43361e592971172f
huggingface.co/lowunderabove/Ocean-yolo/tree/a3719c609eeaf60251cd4c8e43361e592971172f

Verified Sep 27

Download files

Model artifacts

3 artifacts

coral_detector/best.pt

pt · 13.8 MB · SHA-256 a04c8893968e…086d · Hugging Face

Download file

fish_detector/best.pt

pt · 13.9 MB · SHA-256 abfe7fc8f191…11b8 · Hugging Face

Download file

sonar_detector/best.pt

pt · 8.10 MB · SHA-256 7d651083a1ec…a6c2 · Hugging Face

Download file

Source excerpts

2 excerpts

--- language: en license: apache-2.0 library_name: yolov5 tags: - yolov5 - object-detection - fish-detection - coral-detection - sonar-detection - oceangpt-x --- # Ocean-yolo: Marine Object Detectors Specialized YOLOv5 detection models for fine-grained localization and classification of marine targets. Invoked after the routing stage. ## Model Weights | File | Task | Classes | Architecture | |------|------|---------|--------------| | `sonar_detector/best.pt` | Sonar target detection | 15 sonar categories | YOLOv5 | | `fish_detector/best.pt` | Fish species/object detection | Multiple fish classes | YOLOv5 | | `coral_detector/best.pt` | Coral species/object detection | Multiple coral classes | YOLOv5 | ## Usage Requires [YOLOv5](https://github.com/ultralytics/yolov5). ```python import torch # Load detector (e.g., Fish) model = torch.hub.load("ultralytics/yolov5", "custom", path="fish_detector/best.pt", force_reload=True) # Inference results = model("input.jpg", conf=0.5, iou=0.45) results.print()

Source context: 0 downloads · 0 likes · Pipeline object-detection · Library yolov5 · Repo lowunderabove/Ocean-yolo