[LEADERG AI ZOO]Jupyter-Image-Segmentation-MaskRCNN-Keras

Language:

繁體中文

 

 

 

[Introduction]

 

The MaskRCNN algorithm is used to count and segment image objects, which can be applied to medical image analysis, fish image analysis, biological image analysis, advanced driving assistance systems, autonomous vehicles, factory defect detection, etc.

 

[Instruction]

 

The main process is:

label image -> training image -> inference image

 

1. 1_annotation_via_json.ipynb

Open the web page for image annotation.

 

parameter:

--port: 8801 is the port used to label the webpage. If the port is occupied by the user, please change another port value by yourself

 

2. 2_delete_log.ipynb

Delete the log folder.

 

3. 3_kill_tensorboard.ipynb

Before using tensorboard, close the old tensorboard first.

 

4. 4_train.ipynb

Start training.

 

parameter:

--dataset: training dataset path

--weights_path: pre-training model path

--weights_dir: training model storage location

--predefined_classes_txt: all tag category names, need to include background category

--logs: folder location for storing training information

 

5. 5_tensorboard.ipynb

Use tensorboard to check the training status.

After reading the training status, please execute 3_kill_tensorboard.ipynb again to close tensorboard.

 

parameter:

--logs: need to be the same as the value set by --logs in 4_train.ipynb

 

6. 6_inference.ipynb

Inferring a single image.

 

parameter:

--weights: inference model path

--image: infer the image path

--predefined_classes_txt: the name of the category, which must be exactly the same as the value set during training

 

MaskRCNN.png

 

7. 7_evaluation_mAP.ipynb

Calculate the image folder mAP.

 

parameter:

--weights_path: Inference model path

--DATA_DIR: Dataset location

--PREDEFINED_CLASSES_PATH: the category name, which must be exactly the same as the value set during training

--Inference_DATA_DIR: the name of the folder to be calculated. There are two types: train and val. If there is a test folder in the data set location, you can also set test

 

8. 8_inference_api.ipynb

Use web pages for image inferences. If the port value is not changed, execute 9_inference_api_browser.ipynb to open the web page.

 

parameter:

--port: infer the port used by the webpage. If the port is occupied by the user, please change another port value by yourself

--weights_path: inference model path

--predefined_classes_txt: the name of the category, which must be exactly the same as the value set during training


Recommended Article

1.
LEADERG APP - Starter AI Software (No Code, APP User Interface)

2.
LEADERG AI ZOO - Advanced AI Software (Low Code, Jupyter Lab User Interface)

3.
LEADERG AI Computer ( Deep Learning, PC, workstation, server, NVIDIA GPU, TESLA A100, RTX-3090-24G, Intel VPU, GPU Server

4.
LEADERG AI Education

How to Buy

Welcome to contact us for quotation. We will help you buy right products.
Email: leaderg@leaderg.com

Thanks for our customers

Taiwan University, Tsing Hua University, Yang Ming Chiao Tung University, Cheng Kung University, Taipei Medical University, Taipei University of Nursing and Health Sciences, National Chung Hsing University, Chi Nan University, Ilan University, United University, Defence University, Naval Academy, Feng Chia University, Chang Gung University, I-Shou University, Shih Chien University, Taiwan University of Science and Technology, Taichung University of Science and Technology, Yunlin University of Science and Technology, Chin-Yi University of Science, Formosa University, Pintung University of Science and Technology, Kaohsiung University of Science and Technology, Chaoyang University of Technology, Ming Chi University of Technology, Southern Taiwan University of Science and Technology, Taipei Veterans General Hospital, Chang Gung Medical Foundation, Tzu Chi Medical Foundation, E-Da Hospital, Chung-Shan Institute of Science and Technology, Armaments Bureau, Ministry of Justice Investigation Bureau, Institute of Nuclear Energy Research, Endemic Species Research Institute, Institute of Labor, Occupational Safety And Health, Metal Industries Research & Development Centre, Taiwan Instrument Research Institute, Automotive Research & Testing Center, Taiwan Water Corporation, Taiwan Semiconductor Manufacturing Co., Ltd., United Microelectronics Corp., Nanya Technology, Winbond Electronics Corp., Xintec Inc., Arima Lasers Corporation, AU Optronics Corporation, Innolux Corporation, HannStar Display Corporation, Formosa Plastics Group., Formosa Technologies Corporation, Nan Ya Plastics Corp., Formosa Chemicals & Fibre Corporation, Chinese Petroleum Corporation, Logitech, ELAN Microelectronics Corp., Lextar Electronics Corporation, Darfon Electronics Corp., WPG Holdings, Mirle Automation Corporation, Symtek Automation Asia Co., Ltd, ChipMOS Technologies Inc., Dynapack International Technology Corporation, Primax Electronics Ltd., Grade Upon Technology Corp., AAEON Technology Inc., Stark Technology, Inc., Horng Terng Automation Co., Ltd., Zhen Ding Technology Holding Ltd, Boardtek Electronics Corporation, MiTAC International Corporation, Allion Labs, Inc., Sound Land Corp., Hong Hu Tech, etc.