MMLab-dataset_analysis

数据分析工具

这里写目录标题

• 数据分析工具
• • dataset_analysis.py
  • • 数据可视化分析
  • benchmark.py
  • browse_coco_json.py
  • browse_dataset.py
  • Optimize_anchors

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

 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}')