Skip to content

Commit 6e51788

Browse files
committed
更新文档中关于曲线绘制方法的介绍。
1 parent 59735d0 commit 6e51788

File tree

1 file changed

+5
-5
lines changed

1 file changed

+5
-5
lines changed

readme.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -38,9 +38,9 @@ A Python-based image binary segmentation evaluation toolbox.
3838
- maximum/average/adaptive Dice
3939
- maximum/average/adaptive Specificity
4040
- maximum/average/adaptive BER
41-
- Fmeasure-Threshold Curve
42-
- Emeasure-Threshold Curve
43-
- Precision-Recall Curve
41+
- Fmeasure-Threshold Curve (执行 `eval.py` 请指定指标 `fmeasure`)
42+
- Emeasure-Threshold Curve (执行 `eval.py` 请指定指标 `em`)
43+
- Precision-Recall Curve (执行 `eval.py` 请指定指标 `precision``recall`,这一点不同于以前的版本,因为 `precision``recall` 的计算被从 `fmeasure` 中独立出来了)
4444
+ 支持评估*二值图像*, 例如常见的二值分割任务.
4545
- binary Fmeasure
4646
- binary Precision
@@ -195,10 +195,10 @@ python tools/check_path.py --method-jsons configs/methods/rgb-sod/rgb_sod_method
195195
# --curves-npy 输出曲线数据到 output/rgb_sod/curves.npy
196196
# --record-txt 输出评估结果文本到 output/rgb_sod/results.txt
197197
# --record-xlsx 输出评估结果到excel文档 output/rgb_sod/results.xlsx
198-
# --metric-names 所有结果仅包含给定指标的信息
198+
# --metric-names 所有结果仅包含给定指标的信息, 涉及到曲线的四个指标分别为 fmeasure em precision recall
199199
# --include-methods 评估过程仅包含 configs/methods/rgb-sod/rgb_sod_methods.json 中的给定方法
200200
# --include-datasets 评估过程仅包含 configs/datasets/rgb_sod.json 中的给定数据集
201-
python eval.py --dataset-json configs/datasets/rgb_sod.json --method-json configs/methods/rgb-sod/rgb_sod_methods.json --metric-npy output/rgb_sod/metrics.npy --curves-npy output/rgb_sod/curves.npy --record-txt output/rgb_sod/results.txt --record-xlsx output/rgb_sod/results.xlsx --metric-names sm wfm mae fmeasure em --include-methods MINet_R50_2020 GateNet_2020 --include-datasets PASCAL-S ECSSD
201+
python eval.py --dataset-json configs/datasets/rgb_sod.json --method-json configs/methods/rgb-sod/rgb_sod_methods.json --metric-npy output/rgb_sod/metrics.npy --curves-npy output/rgb_sod/curves.npy --record-txt output/rgb_sod/results.txt --record-xlsx output/rgb_sod/results.xlsx --metric-names sm wfm mae fmeasure em precision recall --include-methods MINet_R50_2020 GateNet_2020 --include-datasets PASCAL-S ECSSD
202202

203203
# 得到曲线数据文件,即这里的 output/rgb_sod/curves.npy 文件后,就可以开始绘制图像了
204204

0 commit comments

Comments
 (0)