mirror of
https://github.com/THU-MIG/yolov10.git
synced 2025-05-23 13:34:23 +08:00
ultralytics 8.0.223 add YOLOv8-Ghost P2 and P6 variants (#6826)
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Muhammad Rizwan Munawar <chr043416@gmail.com> Co-authored-by: Awsome <1579093407@qq.com>
This commit is contained in:
Glenn Jocher
GitHub
parent
742cbc1b4e
commit
d74a5a9499
2
.github/workflows/ci.yaml
vendored
2
.github/workflows/ci.yaml
vendored
@ -225,7 +225,7 @@ jobs:
|
||||
run:
|
||||
shell: bash -el {0}
|
||||
steps:
|
||||
- uses: conda-incubator/setup-miniconda@v2
|
||||
- uses: conda-incubator/setup-miniconda@v3
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
mamba-version: "*"
|
||||
|
||||
@ -12,6 +12,7 @@
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics Code Coverage"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 Citation"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker Pulls"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
@ -12,6 +12,7 @@
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics Code Coverage"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 Citation"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker Pulls"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics، YOLOv8، كشف الكائنات، تجزئة الصور
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics Code Coverage"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 Citation"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker Pulls"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, Objekterkennung, Bildsegmentierung, maschinelles
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics Code Coverage"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 Zitation"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker Ziehungen"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Auf Gradient ausführen"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="In Colab öffnen"></a>
|
||||
|
||||
@ -84,6 +84,7 @@ After performing the [Segment Task](../tasks/segment.md), it's sometimes desirab
|
||||
4. Start with generating a binary mask from the source image and then draw a filled contour onto the mask. This will allow the object to be isolated from the other parts of the image. An example from `bus.jpg` for one of the detected `person` class objects is shown on the right.
|
||||
|
||||
{ width="240", align="right" }
|
||||
|
||||
``` { .py .annotate }
|
||||
# Create binary mask
|
||||
b_mask = np.zeros(img.shape[:2], np.uint8)
|
||||
@ -148,7 +149,7 @@ After performing the [Segment Task](../tasks/segment.md), it's sometimes desirab
|
||||
|
||||
### Object Isolation Options
|
||||
|
||||
!!! Example ""
|
||||
!!! example ""
|
||||
|
||||
=== "Black Background Pixels"
|
||||
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, object detection, image segmentation, machine lea
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics Code Coverage"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 Citation"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker Pulls"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
@ -12,6 +12,17 @@ YOLOv8 is the latest iteration in the YOLO series of real-time object detectors,
|
||||
|
||||
|
||||
|
||||
<p align="center">
|
||||
<br>
|
||||
<iframe width="720" height="405" src="https://www.youtube.com/embed/Na0HvJ4hkk0"
|
||||
title="YouTube video player" frameborder="0"
|
||||
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
|
||||
allowfullscreen>
|
||||
</iframe>
|
||||
<br>
|
||||
<strong>Watch:</strong> Ultralytics YOLOv8 Model Overview
|
||||
</p>
|
||||
|
||||
## Key Features
|
||||
|
||||
- **Advanced Backbone and Neck Architectures:** YOLOv8 employs state-of-the-art backbone and neck architectures, resulting in improved feature extraction and object detection performance.
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, detección de objetos, segmentación de imágenes
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Cobertura de código de Ultralytics"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="Cita de YOLOv8"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Descargas de Docker"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Ejecutar en Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Abrir en Colab"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, détection d'objets, segmentation d'images, appre
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Couverture de code Ultralytics"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="Citation YOLOv8"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Téléchargements Docker"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Exécuter sur Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Ouvrir dans Colab"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, वस्तु पता लगाना, छव
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics Code Coverage"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 Citation"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker Pulls"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, オブジェクト検出, 画像セグメンテ
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics コードカバレッジ"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 引用情報"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker プル"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Gradient上で実行"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colabで開く"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, 객체 탐지, 이미지 분할, 기계 학습,
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics 코드 커버리지"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 인용"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker 당기기"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, detecção de objetos, segmentação de imagens,
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Cobertura de Código da Ultralytics"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="Citação do YOLOv8"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Contagem de Pulls no Docker"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Executar no Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Abrir no Colab"></a>
|
||||
|
||||
@ -28,6 +28,7 @@ keywords: Ultralytics, YOLOv8, обнаружение объектов, сегм
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Покрытие кода Ultralytics"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="Цитирование YOLOv8"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Загрузки Docker"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Запустить на Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Открыть в Colab"></a>
|
||||
|
||||
@ -30,6 +30,7 @@ keywords: Ultralytics, YOLOv8, 目标检测, 图像分割, 机器学习, 深度
|
||||
<a href="https://codecov.io/github/ultralytics/ultralytics"><img src="https://codecov.io/github/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY" alt="Ultralytics Code Coverage"></a>
|
||||
<a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv8 Citation"></a>
|
||||
<a href="https://hub.docker.com/r/ultralytics/ultralytics"><img src="https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker" alt="Docker Pulls"></a>
|
||||
<a href="https://ultralytics.com/discord"><img alt="Discord" src="https://img.shields.io/discord/1089800235347353640?logo=discord&logoColor=white&label=Discord&color=blue"></a>
|
||||
<br>
|
||||
<a href="https://console.paperspace.com/github/ultralytics/ultralytics"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a>
|
||||
<a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
|
||||
__version__ = '8.0.222'
|
||||
__version__ = '8.0.223'
|
||||
|
||||
from ultralytics.models import RTDETR, SAM, YOLO
|
||||
from ultralytics.models.fastsam import FastSAM
|
||||
|
||||
54
ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml
Normal file
54
ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml
Normal file
@ -0,0 +1,54 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
# YOLOv8 object detection model with P2-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
|
||||
# [depth, width, max_channels]
|
||||
n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p2 summary: 491 layers, 2033944 parameters, 2033928 gradients, 13.8 GFLOPs
|
||||
s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p2 summary: 491 layers, 5562080 parameters, 5562064 gradients, 25.1 GFLOPs
|
||||
m: [0.67, 0.75, 768] # YOLOv8m-ghost-p2 summary: 731 layers, 9031728 parameters, 9031712 gradients, 42.8 GFLOPs
|
||||
l: [1.00, 1.00, 512] # YOLOv8l-ghost-p2 summary: 971 layers, 12214448 parameters, 12214432 gradients, 69.1 GFLOPs
|
||||
x: [1.00, 1.25, 512] # YOLOv8x-ghost-p2 summary: 971 layers, 18664776 parameters, 18664760 gradients, 103.3 GFLOPs
|
||||
|
||||
# YOLOv8.0-ghost backbone
|
||||
backbone:
|
||||
# [from, repeats, module, args]
|
||||
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
|
||||
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
|
||||
- [-1, 3, C3Ghost, [128, True]]
|
||||
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
|
||||
- [-1, 6, C3Ghost, [256, True]]
|
||||
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
|
||||
- [-1, 6, C3Ghost, [512, True]]
|
||||
- [-1, 1, GhostConv, [1024, 3, 2]] # 7-P5/32
|
||||
- [-1, 3, C3Ghost, [1024, True]]
|
||||
- [-1, 1, SPPF, [1024, 5]] # 9
|
||||
|
||||
# YOLOv8.0-ghost-p2 head
|
||||
head:
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
|
||||
- [-1, 3, C3Ghost, [512]] # 12
|
||||
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
|
||||
- [-1, 3, C3Ghost, [256]] # 15 (P3/8-small)
|
||||
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 2], 1, Concat, [1]] # cat backbone P2
|
||||
- [-1, 3, C3Ghost, [128]] # 18 (P2/4-xsmall)
|
||||
|
||||
- [-1, 1, GhostConv, [128, 3, 2]]
|
||||
- [[-1, 15], 1, Concat, [1]] # cat head P3
|
||||
- [-1, 3, C3Ghost, [256]] # 21 (P3/8-small)
|
||||
|
||||
- [-1, 1, GhostConv, [256, 3, 2]]
|
||||
- [[-1, 12], 1, Concat, [1]] # cat head P4
|
||||
- [-1, 3, C3Ghost, [512]] # 24 (P4/16-medium)
|
||||
|
||||
- [-1, 1, GhostConv, [512, 3, 2]]
|
||||
- [[-1, 9], 1, Concat, [1]] # cat head P5
|
||||
- [-1, 3, C3Ghost, [1024]] # 27 (P5/32-large)
|
||||
|
||||
- [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)
|
||||
56
ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml
Normal file
56
ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml
Normal file
@ -0,0 +1,56 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
# YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
|
||||
|
||||
# Parameters
|
||||
nc: 80 # number of classes
|
||||
scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
|
||||
# [depth, width, max_channels]
|
||||
n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p6 summary: 529 layers, 2901100 parameters, 2901084 gradients, 5.8 GFLOPs
|
||||
s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p6 summary: 529 layers, 9520008 parameters, 9519992 gradients, 16.4 GFLOPs
|
||||
m: [0.67, 0.75, 768] # YOLOv8m-ghost-p6 summary: 789 layers, 18002904 parameters, 18002888 gradients, 34.4 GFLOPs
|
||||
l: [1.00, 1.00, 512] # YOLOv8l-ghost-p6 summary: 1049 layers, 21227584 parameters, 21227568 gradients, 55.3 GFLOPs
|
||||
x: [1.00, 1.25, 512] # YOLOv8x-ghost-p6 summary: 1049 layers, 33057852 parameters, 33057836 gradients, 85.7 GFLOPs
|
||||
|
||||
# YOLOv8.0-ghost backbone
|
||||
backbone:
|
||||
# [from, repeats, module, args]
|
||||
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
|
||||
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
|
||||
- [-1, 3, C3Ghost, [128, True]]
|
||||
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
|
||||
- [-1, 6, C3Ghost, [256, True]]
|
||||
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
|
||||
- [-1, 6, C3Ghost, [512, True]]
|
||||
- [-1, 1, GhostConv, [768, 3, 2]] # 7-P5/32
|
||||
- [-1, 3, C3Ghost, [768, True]]
|
||||
- [-1, 1, GhostConv, [1024, 3, 2]] # 9-P6/64
|
||||
- [-1, 3, C3Ghost, [1024, True]]
|
||||
- [-1, 1, SPPF, [1024, 5]] # 11
|
||||
|
||||
# YOLOv8.0-ghost-p6 head
|
||||
head:
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
|
||||
- [-1, 3, C3Ghost, [768]] # 14
|
||||
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
|
||||
- [-1, 3, C3Ghost, [512]] # 17
|
||||
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
|
||||
- [-1, 3, C3Ghost, [256]] # 20 (P3/8-small)
|
||||
|
||||
- [-1, 1, GhostConv, [256, 3, 2]]
|
||||
- [[-1, 17], 1, Concat, [1]] # cat head P4
|
||||
- [-1, 3, C3Ghost, [512]] # 23 (P4/16-medium)
|
||||
|
||||
- [-1, 1, GhostConv, [512, 3, 2]]
|
||||
- [[-1, 14], 1, Concat, [1]] # cat head P5
|
||||
- [-1, 3, C3Ghost, [768]] # 26 (P5/32-large)
|
||||
|
||||
- [-1, 1, GhostConv, [768, 3, 2]]
|
||||
- [[-1, 11], 1, Concat, [1]] # cat head P6
|
||||
- [-1, 3, C3Ghost, [1024]] # 29 (P6/64-xlarge)
|
||||
|
||||
- [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)
|
||||
@ -345,6 +345,7 @@ class BasePredictor:
|
||||
else: # 'video' or 'stream'
|
||||
frames_path = f'{save_path.split(".", 1)[0]}_frames/'
|
||||
if self.vid_path[idx] != save_path: # new video
|
||||
if self.args.save_frames:
|
||||
Path(frames_path).mkdir(parents=True, exist_ok=True)
|
||||
self.vid_path[idx] = save_path
|
||||
self.vid_frame[idx] = 0
|
||||
@ -363,6 +364,7 @@ class BasePredictor:
|
||||
self.vid_writer[idx].write(im0)
|
||||
|
||||
# Write frame
|
||||
if self.args.save_frames:
|
||||
cv2.imwrite(f'{frames_path}{self.vid_frame[idx]}.jpg', im0)
|
||||
self.vid_frame[idx] += 1
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user