Update model card; add example result image

README.md

@@ -68,8 +68,8 @@ which is why they are large.
 | `detr_finetune/` | `checkpoint.pth` | DETR (baseline) | 18 | 0.536 | 0.536 |
 
 "Test AP" is COCO box AP on the test split (ICPR 2022 PMC split 3, 381 images) of the refined PMC dataset. The
-"re-evaluated" column was measured in October 2026 with the files in this repo and `tools/test.py`, to confirm that the
-uploaded checkpoints reproduce the paper. The intermediate ablation models (PCE only, VCE + PCE without the loss
+"re-evaluated" column was measured in October 2026 with the files in this repo and `tools/test.py` (commands below),
+to confirm that the uploaded checkpoints reproduce the paper. The intermediate ablation models (PCE only, VCE + PCE without the loss
 changes) were not released.
 
 The bar detector was fine-tuned from CACHED on the bar-chart subset of PMC. The paper reports it with the chart
@@ -169,7 +169,8 @@ Then download the test data from [`Pengyu965/ChartDete-PMC2022`](https://hugging
 and evaluate. This reproduces the AP in the table above:
 
 ```bash
-hf download Pengyu965/ChartDete-PMC2022 --repo-type dataset --include "pmc_coco/*" --local-dir data/pmc_2022
+hf download Pengyu965/ChartDete-PMC2022 pmc_coco.zip --repo-type dataset --local-dir data/pmc_2022
+unzip -q data/pmc_2022/pmc_coco.zip -d data/pmc_2022/
 
 python tools/test.py \
     work_dirs/cascade_rcnn_swin-t_fpn_LGF_VCE_PCE_coco_focalsmoothloss/cascade_rcnn_swin-t_fpn_LGF_VCE_PCE_coco_focalsmoothloss.py \