Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tucan9389/objectdetection-coreml
An example running Object Detection using Core ML (YOLOv8, YOLOv5, YOLOv3, MobileNetV2+SSDLite)
https://github.com/tucan9389/objectdetection-coreml
coreml object-detection ssd-mobilenet yolov3 yolov3-tiny yolov5 yolov8
Last synced: about 3 hours ago
JSON representation
An example running Object Detection using Core ML (YOLOv8, YOLOv5, YOLOv3, MobileNetV2+SSDLite)
- Host: GitHub
- URL: https://github.com/tucan9389/objectdetection-coreml
- Owner: tucan9389
- License: mit
- Created: 2019-01-31T17:13:24.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2023-07-01T13:39:41.000Z (over 1 year ago)
- Last Synced: 2024-08-02T13:15:36.188Z (2 months ago)
- Topics: coreml, object-detection, ssd-mobilenet, yolov3, yolov3-tiny, yolov5, yolov8
- Language: Swift
- Homepage: https://github.com/motlabs/awesome-ml-demos-with-ios
- Size: 4.6 MB
- Stars: 282
- Watchers: 4
- Forks: 47
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ObjectDetection-CoreML
> supporting models: [`YOLOv8`](https://github.com/ultralytics/yolov5), [`YOLOv5`](https://github.com/ultralytics/yolov5), [`YOLOv3`](https://github.com/ultralytics/yolov3), `MobileNetV2+SSDLite`
This project is Object Detection on iOS with Core ML.
If you are interested in iOS + Machine Learning, visit [here](https://github.com/motlabs/iOS-Proejcts-with-ML-Models) you can see various DEMOs.
## Requirements
- Xcode 10.3+
- iOS 13.0+
- Swift 4.2
## How To Build and Run the Project
### 1. Clone the project
```shell
git clone https://github.com/tucan9389/ObjectDetection-CoreML
```
### 2. Prepare Core ML model
- You can download COCO models or another model from [here](#model-size-minimum-ios-version-download-link)
> Or if you want to make and use model with custom dataset,
> 1. follow [roboflow tutorial from scratch](https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/) or [yolov5 repo's tutorial](https://github.com/ultralytics/yolov5/issues/12)
> 2. and convert the `.pt` model to `.mlmodel` model with [our issue](https://github.com/tucan9389/ObjectDetection-CoreML/issues/6#issuecomment-1235192089).
### 3. Add the model to the project
By default, the project uses the `yolov8s` model. If you want to use another model, you can replace the model file in the project.
### 4. Set model name properly in `ViewController.swift`
### 5. Build and Run
## How To Run with your own model
### 1. Convert your model to Core ML
> At this moment(23.04.08), there is error when converting yolov8 models to Core ML. Once https://github.com/ultralytics/ultralytics/pull/1791 is merged, you can use the following steps. (Or you can use [this PR](https://github.com/ultralytics/ultralytics/pull/1898) alternatively.)
#### Pre-requirements
```shell
pip install ultralytics
pip install coremltools
```
#### Option 1) With shell
```shell
yolo export model=yolov8n.pt format=coreml nms
```
#### Option 2) With python script
```python
# mian.py
from ultralytics import YOLO
if __name__ == '__main__':
model = YOLO("yolov8n.pt", task='detect') # load a pretrained model
model.overrides['nms'] = True
success = model.export(format="coreml") # export the model to CoreML format
```
```shell
# in terminal
python main.py
# then you can see the `.mlpackage` or `.mlmodel` file in your current directory
# (btw you can check your current directory with `pwd` command)
```
### 2. Follow the steps above from Step 3
## Models
### Model Matadata
### Model Size, Minimum iOS Version, Download Link
Model | Size
(MB) | Minimum
iOS Version | Download
Link | Trained Dataset
:---- | ----: | :----: | ---- | --- |
yolov8n.mlmodel | 12.7 | iOS14 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov8-models/yolov8n.mlpackage.zip)
yolov8s.mlmodel | 44.7 | iOS14 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov8-models/yolov8s.mlpackage.zip)
yolov8m.mlmodel | 52.1 | iOS14 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov8-models/yolov8m.mlpackage.zip)
yolov8l.mlmodel | 87.8 | iOS14 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov8-models/yolov8l.mlpackage.zip)
yolov8x.mlmodel | 272.9 | iOS14 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov8-models/yolov8x.mlpackage.zip)
yolov5n.mlmodel | 7.52 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5n.mlmodel) | [COCO](#trained-dataset-infos)
yolov5s.mlmodel | 28.0 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5s.mlmodel) | [COCO](#trained-dataset-infos)
yolov5m.mlmodel | 81.2 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5m.mlmodel) | [COCO](#trained-dataset-infos)
yolov5l.mlmodel | 178.0 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5l.mlmodel) | [COCO](#trained-dataset-infos)
yolov5x.mlmodel | 331.0 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5x.mlmodel) | [COCO](#trained-dataset-infos)
yolov5n6.mlmodel | 12.8 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5n6.mlmodel) | [COCO](#trained-dataset-infos)
yolov5s6.mlmodel | 48.5 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5s6.mlmodel) | [COCO](#trained-dataset-infos)
yolov5m6.mlmodel | 137.0 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5m6.mlmodel) | [COCO](#trained-dataset-infos)
yolov5l6.mlmodel | 293.0 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5l6.mlmodel) | [COCO](#trained-dataset-infos)
yolov5x6.mlmodel | 537.0 | iOS13 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov5-models/yolov5x6.mlmodel) | [COCO](#trained-dataset-infos)
YOLOv3.mlmodel | 248.4 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov3-models/YOLOv3.mlmodel) | [COCO](#trained-dataset-infos)
YOLOv3FP16.mlmodel | 124.2 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov3-models/YOLOv3FP16.mlmodel) | [COCO](#trained-dataset-infos)
YOLOv3Int8LUT.mlmodel | 62.2 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov3-models/YOLOv3Int8LUT.mlmodel) | [COCO](#trained-dataset-infos)
YOLOv3Tiny.mlmodel | 35.5 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov3-models/YOLOv3Tiny.mlmodel) | [COCO](#trained-dataset-infos)
YOLOv3TinyFP16.mlmodel | 17.8 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov3-models/YOLOv3TinyFP16.mlmodel) | [COCO](#trained-dataset-infos)
YOLOv3TinyInt8LUT.mlmodel | 8.9 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/yolov3-models/YOLOv3TinyInt8LUT.mlmodel) | [COCO](#trained-dataset-infos)
MobileNetV2_SSDLite.mlmodel | 9.3 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/etc-models/MobileNetV2_SSDLite.mlmodel) | [COCO](#trained-dataset-infos)
ObjectDetector.mlmodel | 63.7 | iOS12 | [Link](https://github.com/tucan9389/ObjectDetection-CoreML/releases/download/etc-models/ObjectDetector.mlmodel) | [6 Label Dataset](#trained-dataset-infos)
#### Trained Dataset Infos
COCO Dataset
- https://github.com/ultralytics/yolov5/blob/9da6d0f9f5bc37fa386b7b82d2a963f94650949a/data/coco.yaml#L17-L97
6 Label Dataset(Apple's DEMO)
- Bagel
- Banana
- Coffee
- Croissant
- Egg
- Waffle
## Performance
> Build Setting:
> Xcoede > Build Settings > Apple Clang - Code Generation > Optimization Level > Fastest [-O3]
### Infernece Time (ms)
| Model vs. Device | 14
Pro | 13
Pro | 12
Pro | 11
Pro | XS | XS
Max | XR | X | 7+ | 7 |
| :---- | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: |
| yolov8n | 15
| yolov8s | 29
| yolov8m | 37
| yolov8l | 45
| yolov8x | 51
| yolov5n | | | 24 | | | | | | | |
| yolov5s | | | 29 | | | | | | | |
| yolov5m | | | 39 | | | | | | | |
| yolov5l | | | 38 | | | | | | | |
| yolov5x | | | 69 | | | | | | | |
| yolov5n6 | | | 24 | | | | | | | |
| yolov5s6 | | | 34 | | | | | | | |
| yolov5m6 | | | 39 | | | | | | | |
| yolov5l6 | | | 41 | | | | | | | |
| yolov5x6 | | | 57 | | | | | | | |
| YOLOv3 | | | 45 | 83 | 108 | 93 | 100 | 356 | 569 | 561 |
| YOLOv3FP16 | | | 44 | 84 | 104 | 89 | 101 | 348 | 572 | 565 |
| YOLOv3Int8LUT | | | 53 | 86 | 101 | 92 | 100 | 337 | 575 | 572 |
| YOLOv3Tiny | | | 36 | 44 | 46 | 41 | 47 | 106 | 165 | 168 |
| YOLOv3TinyFP16 | | | 33 | 44 | 51 | 41 | 44 | 103 | 165 | 167 |
| YOLOv3TinyInt8LUT | | | 39 | 44 | 45 | 39 | 39 | 106 | 160 | 161 |
| MobileNetV2_SSDLite | | | 17 | 18 | 31 | 31 | 31 | 109 | 141 | 134 |
| ObjectDetector | | | 13 | 18 | 24 | 26 | 23 | 63 | 86 | 84 |
### Total Time (ms)
| Model vs. Device | 14
Pro | 13
Pro | 12
Pro | | 11
Pro | XS | XS
Max | XR | X | 7+ | 7 |
| :---- | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: |
| yolov8n | 15
| yolov8s | 31
| yolov8m | 39
| yolov8l | 47
| yolov8x | 52
| yolov5n | | | 26 | | | | | | | |
| yolov5s | | | 31 | | | | | | | |
| yolov5m | | | 41 | | | | | | | |
| yolov5l | | | 39 | | | | | | | |
| yolov5x | | | 72 | | | | | | | |
| yolov5n6 | | | 25 | | | | | | | |
| yolov5s6 | | | 36 | | | | | | | |
| yolov5m6 | | | 41 | | | | | | | |
| yolov5l6 | | | 42 | | | | | | | |
| yolov5x6 | | | 59 | | | | | | | |
| YOLOv3 | | | 46 | 84 | 108 | 93 | 100 | 357 | 569 | 561 |
| YOLOv3FP16 | | | 45 | 85 | 104 | 89 | 101 | 348 | 572 | 565 |
| YOLOv3Int8LUT | | | 54 | 86 | 102 | 92 | 102 | 338 | 576 | 573 |
| YOLOv3Tiny | | | 37 | 45 | 46 | 42 | 48 | 106 | 166 | 169 |
| YOLOv3TinyFP16 | | | 35 | 45 | 51 | 41 | 44 | 104 | 165 | 167 |
| YOLOv3TinyInt8LUT | | | 41 | 45 | 45 | 39 | 40 | 107 | 160 | 161 |
| MobileNetV2_SSDLite | | | 19 | 19 | 32 | 31 | 32 | 109 | 142 | 134 |
| ObjectDetector | | | 14 | 18 | 25 | 26 | 23 | 64 | 87 | 85 |
### FPS
| Model vs. Device | 14
Pro | 13
Pro | 12
Pro | | 11
Pro | XS | XS
Max | XR | X | 7+ | 7 |
| :---- | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: | ----: |
| yolov8n | 38
| yolov8s | 14
| yolov8m | 14
| yolov8l | 14
| yolov8x | 13
| yolov5n | | | 19 | | | | | | | |
| yolov5s | | | 14 | | | | | | | |
| yolov5m | | | 13 | | | | | | | |
| yolov5l | | | 14 | | | | | | | |
| yolov5x | | | 7 | | | | | | | |
| yolov5n6 | | | 19 | | | | | | | |
| yolov5s6 | | | 14 | | | | | | | |
| yolov5m6 | | | 13 | | | | | | | |
| yolov5l6 | | | 14 | | | | | | | |
| yolov5x6 | | | 13 | | | | | | | |
| YOLOv3 | | | 12 | 9 | 8 | 10 | 9 | 2 | 1 | 1 |
| YOLOv3FP16 | | | 13 | 9 | 9 | 10 | 8 | 2 | 1 | 1 |
| YOLOv3Int8LUT | | | 14 | 9 | 9 | 10 | 9 | 2 | 1 | 1 |
| YOLOv3Tiny | | | 14 | 14 | 21 | 22 | 20 | 8 | 5 | 5 |
| YOLOv3TinyFP16 | | | 14 | 14 | 19 | 23 | 21 | 9 | 5 | 5 |
| YOLOv3TinyInt8LUT | | | 11 | 14 | 21 | 24 | 23 | 8 | 5 | 5 |
| MobileNetV2_SSDLite | | | 19 | 29 | 23 | 23 | 23 | 8 | 6 | 6 |
| ObjectDetector | | | 17 | 29 | 23 | 23 | 24 | 14 | 10 | 11 |
## See also
- [motlabs/awesome-ml-demos-with-ios](https://github.com/motlabs/awesome-ml-demos-with-ios)
: The challenge using machine learning model created from tensorflow on iOS
- [Machine Learning - Models - Apple Developer](https://developer.apple.com/machine-learning/models)
- [hollance/coreml-survival-guide](https://github.com/hollance/coreml-survival-guide)
- [vonholst/SSDMobileNet_CoreML](https://github.com/vonholst/SSDMobileNet_CoreML)
: iOS project for object detection(SSDMobileNet V1) using Core ML.
- [ultralytics/ultralytics](https://github.com/ultralytics/ultralytics)
: YOLOv8 repository
- [ultralytics/yolov5](https://github.com/ultralytics/yolov5)
: YOLOv5 repository