MMLab-dataset_analysis

数据分析工具

这里写目录标题

数据分析工具

mmyolo、mmsegmentation等提供了数据集分析工具

dataset_analysis.py

数据采用coco格式数据

根据配置文件分析全部数据类型或指定类型的Bbox_num、bbox_wh\bbox_wh_ratio、bbox_area

示例数据采用的是讯飞X光安检物品监测数据集，通过结果可以看出Knife、wrench、powerbank等小物品的数据相对较少，Knife类别最少，存在显著的类别不平衡问题。

数据可视化分析

bbox_area
bbox_ratio
bbox_wh

benchmark.py

测试模型性能：推理速度

!python /root/mmyolo/tools/analysis_tools/browse_coco_json.py --data-root /root/autodl-tmp/train --img-dir /root/autodl-tmp/train/images/ --ann-file /root/autodl-tmp/train/annotations/instances_train2014.json

browse_coco_json.py

将数据集与标签进行可视化

browse_dataset.py

-将数据可视化保存输出到文件夹下,包含两种模式

-m：'original', 'transformed', 'pipeline'

'original'：金输出原始图像

'transformed'：输出变换后的图像

'pipeline'：输出数据增流各个阶段的图像

Optimize_anchors

通过分析数据，优化先验anchor的设置，仅支持YOLOAnchorGenerator

"""Optimize anchor settings on a specific dataset.

This script provides three methods to optimize YOLO anchors including k-means

anchor cluster, differential evolution and v5-k-means. You can use
--algorithm k-means, --algorithm differential_evolution and
--algorithm v5-k-means to switch those methods.

Example:

Use k-means anchor cluster::

    python tools/analysis_tools/optimize_anchors.py ${CONFIG} \
    --algorithm k-means --input-shape ${INPUT_SHAPE [WIDTH HEIGHT]} \
    --out-dir ${OUT_DIR}

Use differential evolution to optimize anchors::

    python tools/analysis_tools/optimize_anchors.py ${CONFIG} \
    --algorithm differential_evolution \
    --input-shape ${INPUT_SHAPE [WIDTH HEIGHT]} \
    --out-dir ${OUT_DIR}

Use v5-k-means to optimize anchors::

    python tools/analysis_tools/optimize_anchors.py ${CONFIG} \
    --algorithm v5-k-means \
    --input-shape ${INPUT_SHAPE [WIDTH HEIGHT]} \
    --prior_match_thr ${PRIOR_MATCH_THR} \
    --out-dir ${OUT_DIR}

该工具默认调用gpu进行数据计算,算法名称还有个小bug，需要注意一下

python 复制代码

 if args.algorithm == 'k-means':
      optimizer = YOLOKMeansAnchorOptimizer(
          dataset=dataset,
          input_shape=input_shape,
          device=args.device,
          num_anchor_per_level=num_anchor_per_level,
          iters=args.iters,
          logger=logger,
          out_dir=args.out_dir)
  elif args.algorithm == 'DE':
      optimizer = YOLODEAnchorOptimizer(
          dataset=dataset,
          input_shape=input_shape,
          device=args.device,
          num_anchor_per_level=num_anchor_per_level,
          iters=args.iters,
          logger=logger,
          out_dir=args.out_dir)
  elif args.algorithm == 'v5-k-means':
      optimizer = YOLOV5KMeansAnchorOptimizer(
          dataset=dataset,
          input_shape=input_shape,
          device=args.device,
          num_anchor_per_level=num_anchor_per_level,
          iters=args.iters,
          prior_match_thr=args.prior_match_thr,
          mutation_args=args.mutation_args,
          augment_args=args.augment_args,
          logger=logger,
          out_dir=args.out_dir)
  else:
      raise NotImplementedError(
          f'Only support k-means and differential_evolution, '
          f'but get {args.algorithm}')