We provide lots of useful tools under the `tools/` directory. In addition, you can also quickly run other open source libraries of OpenMMLab through MIM.
Take MMDetection as an example. If you want to use [print_config.py](https://github.com/open-mmlab/mmdetection/blob/3.x/tools/misc/print_config.py), you can directly use the following commands without copying the source code to the MMYOLO library.
```shell
mim run mmdet print_config [CONFIG]
```
**Note**: The MMDetection library must be installed through the MIM before the above command can succeed.
## Visualization
### Visualize COCO labels
`tools/analysis_tools/browse_coco_json.py` is a script that can visualization to display the COCO label in the picture.
`tools/analysis_tools/browse_dataset.py` helps the user to browse a detection dataset (both images and bounding box annotations) visually, or save the image to a designated directory.
1. Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` to visualize the picture. The picture will pop up directly and be saved to the directory `work dir/browse_ dataset` at the same time:
2. Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` to visualize the picture. The picture will pop up and display directly. Each picture lasts for `10` seconds. At the same time, it will be saved to the directory `work dir/browse_ dataset`:
3. Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` to visualize the picture. The picture will pop up and display directly. Each picture lasts for `10` seconds and the picture will not be saved:
4. Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` to visualize the picture. The picture will not pop up directly, but only saved to the directory `work dir/browse_ dataset`:
`tools/analysis_tools/dataset_analysis.py` help users get the renderings of the four functions, and save the pictures to the `dataset_analysis` folder under the current running directory.
Description of the script's functions:
The data required by each sub function is obtained through the data preparation of `main()`.
Function 1: Generated by the sub function `show_bbox_num` to display the distribution of categories and bbox instances.
1.Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` analyze the dataset, By default,the data loadingt type is `train_dataset`, the area rule is `[0,32,96,1e5]`, generate a result graph containing all functions and save the graph to the current running directory `./dataset_analysis` folder:
2.Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` analyze the dataset, change the data loading type from the default `train_dataset` to `val_dataset` through the `--val-dataset` setting:
3.Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` analyze the dataset, change the display of all generated classes to specific classes. Take the display of `person` classes as an example:
4.Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` analyze the dataset, redefine the area rule through `--area-rule` . Take `30 70 125` as an example, the area rule becomes `[0,30,70,125,1e5]`：
5.Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` analyze the dataset, change the display of four function renderings to only display `Function 1` as an example:
6.Use `config` file `configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py` analyze the dataset, modify the picture saving address to `work_ir/dataset_analysis`:
-`ballon2coco.py` converts the `balloon` dataset (this small dataset is for starters only) to COCO format.
For a detailed description of this script, please see the `Dataset Preparation` section in [From getting started to deployment with YOLOv5](./yolov5_tutorial.md).
1.`image_dir` is the root directory of the yolo-style dataset you need to pass to the script, which should contain `images`, `labels`, and `classes.txt`. `classes.txt` is the class declaration corresponding to the current dataset. One class a line. The structure of the root directory should be formatted as this example shows:
```bash
.
└── $ROOT_PATH
├── classes.txt
├── labels
│ ├── a.txt
│ ├── b.txt
│ └── ...
├── images
│ ├── a.jpg
│ ├── b.png
│ └── ...
└── ...
```
2. The script will automatically check if `train.txt`, `val.txt`, and `test.txt` have already existed under `image_dir`. If these files are located, the script will organize the dataset accordingly. Otherwise, the script will convert the dataset into one file. The image paths in these files must be **ABSOLUTE** paths.
3. By default, the script will create a folder called `annotations` in the `image_dir` directory which stores the converted JSON file. If `train.txt`, `val.txt`, and `test.txt` are not found, the output file is `result.json`. Otherwise, the corresponding JSON file will be generated, named as `train.json`, `val.json`, and `test.json`. The `annotations` folder may look similar to this:
The three scripts under the `tools/` directory can help users convert the keys in the official pre-trained model of YOLO to the format of MMYOLO, and use MMYOLO to fine-tune the model.
The training dataset of the COCO2017 dataset includes 118K images, and the validation set includes 5K images, which is a relatively large dataset. Loading JSON in debugging or quick verification scenarios will consume more resources and bring slower startup speed.
The `extract_subcoco.py` script provides the ability to extract a specified number of images. The user can use the `--num-img` parameter to get a COCO subset of the specified number of images.
Currently, only support COCO2017. In the future will support user-defined datasets of standard coco JSON format.
The root path folder format is as follows:
```text
├── root
│ ├── annotations
│ ├── train2017
│ ├── val2017
│ ├── test2017
```
1. Extract 10 training images and 10 validation images using only 5K validation sets.
