Mask_R-CNN - GitLite

KO | EN

gitlite — search

#self-hosted #github #cloud-native #chatgpt #machine-learning #awesome #pytorch #typescript #automation #nlp

Mask_R-CNN

(★ 15)

A modified version of Mask R-CNN based on Matterport's version. Featuring: polygon annotating mask generation and k-fold cross-validation training.

파일 탐색기

ZIP 다운로드

- annotation.png
- model.png
- __init__.py
- __init__.pyc
- config.py
- model.py
- parallel_model.py
- parse_args.py
- utils.py
- utils.pyc
- visualize.py
- visualize.pyc
- visualize_cv2.py
- demo.ipynb
- export_model.ipynb
- inspect_balloon_data.ipynb
- inspect_balloon_model.ipynb
- inspect_data.ipynb
- inspect_model.ipynb
- inspect_nucleus_data.ipynb
- inspect_nucleus_model.ipynb
- inspect_weights.ipynb
- train_coco.ipynb
- train_shapes.ipynb
annotating_generation.py
dataset.py
environment.yml
evaluation.py
image_detection.py
README.md
training.py
training_with_K_fold.py
video_detection.py

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

명령어 용어집

이 문서에서 사용된 명령어를 모아봤습니다. 낯선 명령어가 있다면 펼쳐서 확인해보세요.

🔍

`conda activate`

설명 보기 ▼

Activate a conda environment.
See also: `conda deactivate`.

conda activate myenv

Activate an existing environment named `myenv`:

conda activate {{path/to/myenv}}

Activate an existing environment located at custom path:

conda activate --stack myenv

Stack `myenv` environment on top of a previous environment making libraries/commands/variables from both accessible:

🔍

`conda env`

설명 보기 ▼

Manage conda environments.

conda env create {{[-f|--file]}} {{path/to/file}}

Create an environment from an environment file (YAML, TXT, etc.):

conda env remove {{[-n|--name]}} {{environment_name}}

Delete an environment and everything in it:

conda env update {{[-f|--file]}} {{path/to/file}} --prune

Update an environment based on an environment file:

🔍

`python3`

설명 보기 ▼

이 명령은 `python`의 별칭입니다.

tldr python

자세한 내용은 원본 명령을 참고하세요:

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

This is an implementation of [**Mask R-CNN**](https://arxiv.org/abs/1703.06870) on Python 3, Keras, and TensorFlow based on Matterport's [**version**](https://github.com/matterport/Mask_RCNN). The model generates bounding boxes and segmentation masks for each instance of an object in the image, with **Feature Pyramid Network (FPN) + ResNet-101** as backbones.

![](https://raw.githubusercontent.com/quanghuy0497/Mask_R-CNN/main/Images/model.png)

## Features:

* Mask R-CNN implementation built on TensorFlow and Keras.
* Model training with _data augmentation_ and _various configuration_.
* **_Custom mAP callback_** during the training process for initial evaluation.
* Training with **_5-fold cross-validation_** strategy.
* Evaluation with mean Average Precision (mAP) on COCO metric `AP@.50:.05:.95` and PASCAL VOC metric `AP@.50`. For more information, read [**here**](https://cocodataset.org/#detection-eval).
* **_Jupyter notebooks examples_** to visualize the detection pipeline at every step and understand more about Mask R-CNN.
* Convert predicted results to the VGG [annotation format](#annotation-format) to expand the dataset for further training. Achieved a **_finer, more accurate mask_** with less labeling time than by handwork (~3 quarters in large-scale).
    * For instance, the comparison between the annotated mask by handwork (**_left_**) and by model's prediction (**_right_**)
        ![](https://raw.githubusercontent.com/quanghuy0497/Mask_R-CNN/main/Images/annotation.png)

## Structure:
It is recommended to organize the dataset folder, testing image/video folder and model weight under same folder as the below structure:

├── notebooks                                 # several notebooks from Matterport's Mask R-CNN
    ├── dataset                                   # place the dataset here
    │   └── <dataset_name>              
    │       ├── train
    │       │   ├── <image_file 1>                # accept .jpg or .jpeg file
    │       │   ├── <image_file 2>
    │       │   ├── ...
    │       │   └── via_export_json.json          # corresponded single annotation file, must be named like this
    │       ├── val
    │       └── test         
    ├── logs                                      # log folder
    ├── mrcnn                                     # model folder
    ├── test                                      # test folder
    │   ├── image
    │   └── video
    ├── trained_weight                            # pre-trained model and trained weight folder
    |   ...
    ├── environment.yml                           # environment setup file
    ├── README.md
    ├── dataset.py                                # dataset configuration
    ├── evaluation.py                             # weight evaluation
    └── training.py                               # training model
    
## Usage:

* Conda environment setup:
    ```bash
        conda env create -f environment.yml
        conda activate mask-rcnn
    ```
 * Training:
    ```bash
    * Train a new model starting from pre-trained weights
        python3 training.py --dataset=/path/to/dataset --weight=/path/to/pretrained/weight.h5
    
    * Resume training a model
        python3 training.py --dataset=/path/to/dataset --continue_train=/path/to/latest/weights.h5
    ```
 * Evaluating:
    ```bash
    python3 evaluation.py --dataset=/path/to/dataset --weights=/path/to/pretrained/weight.h5
    ```
 * Testing
    ```bash
    * Image
        python3 image_detection.py --dataset=/path/to/dataset --weights=/path/to/pretrained/weight.h5 --image=/path/to/image/directory

* Video (update weight path and dataset path in mrcnn.visualize_cv2)
        python3 video_detection.py --video_path = /path/to/testing/video/dir/

```
 * Annotation generating:
    ```bash
    python3 annotating_generation.py --dataset=/path/to/dataset --weights=/path/to/pretrained/weight.h5 --image=/path/to/image/directory
    
    ```
 * View training plot:
    ```bash
    tensorboard --logdir=logs/path/to/trained/dir
    
    ```
     
## Annotation format:

Annotated image for this implementation is created by [VGG Image Annotator](https://www.robots.ox.ac.uk/~vgg/software/via/) with format structure:
```
{ 'filename': '<image_name>.jpg',
           'regions': {
               '0': {
                   'region_attributes': {},
                   'shape_attributes': {
                       'all_points_x': [...],
                       'all_points_y': [...],
                       'name': <class_name>}},
               ... more regions ...
           },
           'size': <image_size>
}
```

## Notes:

* This implementation is well worked under TensorFlow 1.14.0, Keras 2.2.5, Cuda 10.0.130 and CuDNN 7.6.5
* ```dataset.py``` must be modify for other custom dataset.
* Futher training parameters configuration can be read in [**here**](https://github.com/matterport/Mask_RCNN/wiki).
* Pre-trained weight on COCO: download [**here**](https://github.com/matterport/Mask_RCNN/releases/download/v2.0/mask_rcnn_coco.h5) and place it in ```trained_weight\```