Data

Tools

Indexes

Applications

Experiments

Open Source Science

yolov8-apple

An improved YOLOv8 model, termed YOLOv8-Apple, aimed at effectively detecting small-scale apples and handling severe occlusions

https://github.com/embracely/yolov8-apple

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.1%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

An improved YOLOv8 model, termed YOLOv8-Apple, aimed at effectively detecting small-scale apples and handling severe occlusions

Basic Info
  • Host: GitHub
  • Owner: Embracely
  • License: agpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 7.95 MB
Statistics
  • Stars: 6
  • Watchers: 1
  • Forks: 0
  • Open Issues: 2
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Citation

README.md

YOLOv8-Apple

Introduction

YOLOv8-Apple is an improved YOLOv8 model designed to effectively detect small-scale apples and handle severe occlusions. A backbone network was constructed by replacing traditional stride convolutions and pooling layers with SPD-Conv to minimize the loss of fine-grained information, using SEAM to enhance feature representations of unoccluded regions and compensate for occluded ones at the neck, and integrating a lightweight CBAM attention mechanism to strengthen the representation capability of small targets. The results of comprehensive experiments on the MinneApple dataset demonstrate that the mAP of YOLOv8-Apple increases by 3.8%, and MAE and RMSE of counting tasks decrease by 11.8% and 28.8%, respectively.

Frame Structure

Apple Detection Example

Evaluation

Apple Detection and Counting

Below are the detection and counting results under different improvement configurations.

| SPD-Conv | SEAM | CBAM | mAP0.5 | F1 Score | Precision | Recall | MAE | RMSE | |:--------:|:----:|:----:|:------:|:--------:|:---------:|:------:|:----:|:-----:| | | | | 0.725 | 0.709 | 0.753 | 0.670 | 2.97 | 13.28 | | ✔ | | | 0.759 | 0.724 | 0.769 | 0.686 | 2.65 | 11.08 | | | ✔ | | 0.744 | 0.704 | 0.755 | 0.659 | 2.54 | 9.49 | | | | ✔ | 0.738 | 0.722 | 0.758 | 0.688 | 2.89 | 12.24 | | ✔ | ✔ | | 0.763 | 0.730 | 0.761 | 0.704 | 2.77 | 9.29 | | | ✔ | ✔ | 0.747 | 0.710 | 0.754 | 0.670 | 2.98 | 12.80 | | ✔ | | ✔ | 0.764 | 0.717 | 0.766 | 0.673 | 2.95 | 9.29 | | ✔ | ✔ | ✔ | 0.763 | 0.726 | 0.768 | 0.688 | 2.62 | 9.45 |

Environmental Requirements

  1. Create a Python Virtual Environment
    ```bash conda create -n {name} python==3.8

  2. **Activate the Virtual Environment ```bash conda activate {name}

  3. Install Pytorch
    ```bash pip install torch==1.10.0+cu111 torchvision==0.11.0+cu111 torchaudio==0.10.0 \

    -f https://download.pytorch.org/whl/torch_stable.html

Step-Through Example

Installation

  1. Clone this repository
    ```bash git clone https://github.com/Embracely/YOLOv8-Apple.git

Dataset

  1. Download the MinneApple Dataset into the data folder

  2. Convert the dataset’s mask tags YOLO annotation files ```bash

    python mask2yolo.py

Pretrained Model

You can download the pretrained weights at yolov8-apple.pt.

Training

Data Pre-processing

  1. Split the data set

bash python split_dataset.py 2. Converting the format of data set

bash python voc_label.py

Train your model on MinneApple

bash python train.py

Test

bash python test_counting.py

Owner

  • Login: Embracely
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with https://bit.ly/cffinit

cff-version: 1.2.0
title: Ultralytics YOLO
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Glenn
    family-names: Jocher
    affiliation: Ultralytics
    orcid: 'https://orcid.org/0000-0001-5950-6979'
  - family-names: Qiu
    given-names: Jing
    affiliation: Ultralytics
    orcid: 'https://orcid.org/0000-0003-3783-7069'
  - given-names: Ayush
    family-names: Chaurasia
    affiliation: Ultralytics
    orcid: 'https://orcid.org/0000-0002-7603-6750'
repository-code: 'https://github.com/ultralytics/ultralytics'
url: 'https://ultralytics.com'
license: AGPL-3.0
version: 8.0.0
date-released: '2023-01-10'

GitHub Events

Total
  • Watch event: 8
  • Delete event: 6
  • Issue comment event: 24
  • Public event: 1
  • Push event: 33
  • Pull request event: 13
  • Create event: 11
Last Year
  • Watch event: 8
  • Delete event: 6
  • Issue comment event: 24
  • Public event: 1
  • Push event: 33
  • Pull request event: 13
  • Create event: 11

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 0
  • Total pull requests: 8
  • Average time to close issues: N/A
  • Average time to close pull requests: about 2 months
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 2.38
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 8
Past Year
  • Issues: 0
  • Pull requests: 8
  • Average time to close issues: N/A
  • Average time to close pull requests: about 2 months
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 2.38
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 8
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • dependabot[bot] (8)
Top Labels
Issue Labels
Pull Request Labels
Stale (1)

Dependencies

.github/workflows/ci.yaml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • astral-sh/setup-uv v4 composite
  • astral-sh/setup-uv v3 composite
  • codecov/codecov-action v5 composite
  • conda-incubator/setup-miniconda v3 composite
  • slackapi/slack-github-action v2.0.0 composite
  • ultralytics/actions/cleanup-disk main composite
.github/workflows/cla.yml actions
  • contributor-assistant/github-action v2.6.1 composite
.github/workflows/docker.yaml actions
  • actions/checkout v4 composite
  • docker/login-action v3 composite
  • docker/setup-buildx-action v3 composite
  • docker/setup-qemu-action v3 composite
  • slackapi/slack-github-action v2.0.0 composite
  • ultralytics/actions/cleanup-disk main composite
  • ultralytics/actions/retry main composite
.github/workflows/docs.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • astral-sh/setup-uv v4 composite
.github/workflows/format.yml actions
  • ultralytics/actions main composite
.github/workflows/links.yml actions
  • actions/checkout v4 composite
  • ultralytics/actions/retry main composite
.github/workflows/merge-main-into-prs.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
.github/workflows/publish.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • pypa/gh-action-pypi-publish release/v1 composite
  • slackapi/slack-github-action v2.0.0 composite
.github/workflows/stale.yml actions
  • actions/stale v9 composite
examples/YOLO-Series-ONNXRuntime-Rust/Cargo.toml cargo
examples/YOLOv8-ONNXRuntime-Rust/Cargo.toml cargo
docker/Dockerfile docker
  • pytorch/pytorch 2.5.0-cuda12.4-cudnn9-runtime build
pyproject.toml pypi
  • matplotlib >=3.3.0
  • numpy <2.0.0; sys_platform == 'darwin'
  • numpy >=1.23.0
  • opencv-python >=4.6.0
  • pandas >=1.1.4
  • pillow >=7.1.2
  • psutil *
  • py-cpuinfo *
  • pyyaml >=5.3.1
  • requests >=2.23.0
  • scipy >=1.4.1
  • seaborn >=0.11.0
  • torch >=1.8.0
  • torch >=1.8.0,!=2.4.0; sys_platform == 'win32'
  • torchvision >=0.9.0
  • tqdm >=4.64.0
  • ultralytics-thop >=2.0.0