islinxu / vision-process-webui

💡💡💡awesome compute vision app in gradio

vision-process-webui

language: [en ｜ 中文]

---

🎤Introduction

Due to the increasing complexity of the theory and models of computer vision, in order to facilitate intuitive understanding and reproduction, reduce the threshold of use, and quickly verify image processing effects, inspired by the stable-diffusion-webui project in the promotion of the stable-diffusion model application, some models based on tasks such as object detection, image segmentation, and image classification are deployed and demonstrated on Gradio for inference. More people are welcome to contribute and use!

🛜Online running

• ❗️Currently, the app application of this repository has been deployed on OpenXLab,ModelScope and huggingface . Welcome to test and use.

OpenMMLab

• 📦MMYOLO:
• 📦MMDetection:
• 📦MMDetection3D:
• 📦MMSegmentation:
• 📦MMOCR:
• 📦MMRotate:
• 📦MMHuman3D:
• 📦MMAction2:
• 📦MMTracking:
• 📦MMPreTrain:
• 📦MMPose:
• 📦MMagic:
• 📦MMGeneration:
• 📦MMEditing:
• 📦MMFlow:

detectron2

• 📦detectron2:

detrex

• 📦detrex:

modelscope&AdaDet

• 📦DAMO-YOLO:
• 📦DAMO-FD:
• 📦DAMO-OCR:

detection

• 📦yolov8-app:
• 📦yolov5-app:
• 📦yolov3-app:
• 📦yolox-app:
• 📦yolonas-app:
• 📦ppyoloe-app:
• 📦torchvision-detection-webui:

classification

• 📦torchvision-classification-app:
• 📦timm-classification-webui:

segmentation

• 📦torchvision-segmentation-app:
• 📦mobile-sam-app:

🧙performance&demo

🔨OpenMMLab

MMPreTrain	MMYOLO	MMDetection	MMPose
MMSegmentation	MMRotate	MMOCR	MMAction2

🔨detectron2

🔨classification

---

🔨detection

YOLOv8-det	YOLOv8-seg	YOLOv8-seg	YOLOv8-seg

YOLOv3	YOLOv5	YOLOX
YOLO-NAS	PP-YOLOE	RT-Detr

---

🔨segmentation

mobile-sam[point]	mobile-sam[bbox]

---

🆕News

• (2024-05-06): add yolo_world_with_efficientvit_sam
• (2024-05-04): support upload model for inference.
• (2023-09-29): update README.md
• (2023-09-20): detrex、damo-yolo、easy-face
• (2023-09-18): detectron2
• (2023-09-16): mmagic
• (2023-09-14): mmtracking
• (2023-09-12): mmaction2
• (2023-09-10): mmocr、mmroate、mmsegmentation
• (2023-09-08): mmyolo、mmpretrain、mmdetection、mmpose
• (2023-09-07): yolov3、yolov5、yolov8、yolo_nas、yolox、torchvision-detection、mobile-sam、timm-classification
• (2023-09-02): repo init.

🗓support list

Model	Nums	list
yolov3	3	model_list
yolov5	4	model_list
yolox	5	model_list
yolonas	3	model_list
yolov8	4	model_list
timm	20	model_list
torchvision_cls	14	model_list
torchvision_det	6	model_list
detectron2	36	model_list
detrex	61	model_list
mmpretrain	545	model_list
mmyolo	74	model_list
mmdetection	559	model_list
mmsegmentation	622	model_list
mmocr	17	model_list
mmaction2	180	model_list
mmrorate	50	model_list
mmpose	10	model_list
mmagic	14	model_list
damo_face	4	model_list
damo_yolo	8	model_list

🔨classification

• VGG16(src | code)
• AlexNet(src | code)
• ResNet18(src | code)
• ResNet50(src | code)
• ResNet101(src | code)
• ResNet152(src | code)
• GoogLeNet(src | code)
• DenseNet121(src | code)
• MobileNetV2(src | code)
• SqueezeNet(src | code)
• WideResNet50(src | code)
• WideResNet101(src | code)
• InceptionV3(src | code)

🔨detection

• yolov3(src | code)
• yolov4(src | code)
• yolov5(src | code)
• yolov6(src | code)
• yolov7(src | code)
• yolox(src | code))
• ppyoloe(src | code))
• yolo-nas(src | code))
• yolov8(src | code)
• rtdetr-l(src | code))
• fasterrcnn_resnet50_fpn(src | code))
• maskrcnn_resnet50_fpn(src | code))
• keypointrcnn_resnet50_fpn(src | code))
• retinanet_resnet50_fpn(src | code))

---

🔨segmentation

• mobile_sam(src | code)
• fast_sam(src | code)
• DeepLabv3(src | code)
• DeepLabv3+(src | code)
• FCN-ResNet50(src | code)
• FCN-ResNet101(src | code)
• LRR(src | code)
• UNet()

📖Usage

1. install

git clone https://github.com/isLinXu/vision-process-webui.git
cd vision-process-webui
pip install -r requirements.txt

2. download weights

cd weights
cd [model_name]
sh download_weights.sh

model_name=xxxx

3. run

python webui/model_app.py

model_app=classification|detection|segmentation or

cd webui/app
python [model_app].py

model_app=yolov3|yolov5|yolov8|yolonas|ppyoloe|torchvision-detection|torchvision-classification|torchvision-segmentation|mobile-sam|fast-sam

🧾TODO

support more models and libraries

OpenMMLab

• 📦MMYOLO
• 📦MMDetection
• 📦MMDetection3D:
• 📦MMSegmentation:
• 📦MMOCR:
• 📦MMHuman3D:
• 📦MMAction2:
• 📦MMTracking:
• 📦MMRotate:
• 📦MMPreTrain:
• 📦MMPose:
• 📦MMagic:
• 📦MMGeneration:
• 📦MMEditing:
• 📦MMFlow:

detectron2 series

• 📦detectron2:
• 📦detrex:

EasyCV

• 📦Classification:
• 📦Detection:
• 📦Segmentation:
• 📦Pose Estimation

AdaDet

• 📦DAMO-YOLO:
• 📦DAMO-FD:
• building...

gluon-cv

• building...

PaddleDetection

• building...

docker image build

• building...

merge all ui.py in one

• building...

🌸Reference

• stable-diffusion-webui: Stable Diffusion web UI
• torchvision: Datasets, Transforms and Models specific to Computer Vision
• timm: PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
• yolov3: YOLOv3 in PyTorch > ONNX > CoreML > TFLite
• yolov5: YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
• ultralytics: NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
• super-gradients: Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
• MMEngine: OpenMMLab foundational library for training deep learning models.
• MMCV: OpenMMLab foundational library for computer vision.
• MMPreTrain: OpenMMLab pre-training toolbox and benchmark.
• MMagic: OpenMMLab Advanced, Generative and Intelligent Creation toolbox.
• MMDetection: OpenMMLab detection toolbox and benchmark.
• MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
• MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
• MMYOLO: OpenMMLab YOLO series toolbox and benchmark.
• MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
• MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
• MMPose: OpenMMLab pose estimation toolbox and benchmark.
• MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
• MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
• MMRazor: OpenMMLab model compression toolbox and benchmark.
• MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
• MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
• MMTracking: OpenMMLab video perception toolbox and benchmark.
• MMFlow: OpenMMLab optical flow toolbox and benchmark.
• MMEditing: OpenMMLab image and video editing toolbox.
• MMGeneration: OpenMMLab image and video generative models toolbox.
• MMDeploy: OpenMMLab model deployment framework.
• MIM: MIM installs OpenMMLab packages.
• MMEval: OpenMMLab machine learning evaluation library.
• Playground: A central hub for gathering and showcasing amazing projects built upon OpenMMLab.
• detectron2: Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
• detrex: detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.
• gluon-cv:Gluon CV Toolkit
• autogluon: AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data
• EasyCV: An all-in-one toolkit for computer vision
• AdaDet:AdaDet: A Development Toolkit for Object Detection based on ModelScope
• mediapipe:MediaPipe Solutions provides a suite of libraries and tools for you to quickly apply artificial intelligence (AI) and machine learning (ML) techniques in your applications.
• dlib:A toolkit for making real world machine learning and data analysis applications in C++

vision-process-webui's Issues

To create a public link, set `share=True` in `launch()`.

Looking in yolov8_app.py I don't see launch() anywhere

I tried adding it like so

if __name__ == '__main__':
    web_ui = YOLOv8WebUI()
    web_ui.launch(share=True)

But that fails with

Traceback (most recent call last):
  File "/home/vision-process-webui/webui/app/yolov8_app.py", line 102, in <module>
    web_ui.launch(share=True)
TypeError: YOLOv8WebUI.launch() got an unexpected keyword argument 'share'

What file should I be adding 'share=True` to please?

I read this for stable-diffusion-webui but nothing there helped