Upload README.md with huggingface_hub

README.md

@@ -24,9 +24,11 @@ CTW1500, and ICDAR2015.
 
 ## Models and Results
 
-Replacing the ImageNet-pretrained ResNet-50 with the MonkeyOCRv2-AS encoder
-consistently improves F-score over both the baseline and the
-[oCLIP](https://github.com/bytedance/oclip)-pretrained backbone.
+For each detector, three visual backbones are compared under identical
+settings: the original ImageNet-pretrained encoder, the text-specific
+[oCLIP](https://github.com/bytedance/oclip) encoder, and MonkeyOCRv2.
+MonkeyOCRv2 consistently improves F-score across all datasets and detector
+architectures.
 
 ### Total-Text
 
@@ -70,24 +72,6 @@ hf download HB16888/MonkeyOCRv2_det --include "*.pth" --local-dir ./model_weight
 modelscope download --model WangXinhan/MonkeyOCRv2_det --local_dir ./model_weight
 ```
 
-Each checkpoint is the best epoch on the test set, i.e. exactly the row
-reported in the tables above.
-
-| Checkpoint                       | Method               | Dataset    | Epoch | Config                                                                           |
-| -------------------------------- | -------------------- | ---------- | ----: | -------------------------------------------------------------------------------- |
-| dbnet\_r50\_totaltext.pth        | DBNet baseline       | Total-Text |   580 | configs/textdet/dbnet/dbnet\_resnet50\_1200e\_totaltext\_2gpu.py                 |
-| dbnet\_r50-oclip\_totaltext.pth  | DBNet + oCLIP        | Total-Text |   740 | configs/textdet/dbnet/dbnet\_resnet50-oclip\_1200e\_totaltext\_2gpu.py           |
-| dbnet\_mkv2vitae\_totaltext.pth  | DBNet + MonkeyOCRv2  | Total-Text |  1000 | configs/textdet/dbnet/dbnet\_mkv2vitae\_1200e\_totaltext\_2gpu\_adamw\.py        |
-| psenet\_r50\_ctw1500.pth         | PSENet baseline      | CTW1500    |   280 | configs/textdet/psenet/psenet\_resnet50\_fpnf\_600e\_ctw1500\_2gpu.py            |
-| psenet\_r50-oclip\_ctw1500.pth   | PSENet + oCLIP       | CTW1500    |   280 | configs/textdet/psenet/psenet\_resnet50-oclip\_fpnf\_600e\_ctw1500\_2gpu.py      |
-| psenet\_mkv2vitae\_ctw1500.pth   | PSENet + MonkeyOCRv2 | CTW1500    |   120 | configs/textdet/psenet/psenet\_mkv2vitae\_fpnf\_600e\_ctw1500\_4gpu\_adamw\.py   |
-| psenet\_r50\_icdar2015.pth       | PSENet baseline      | ICDAR2015  |   400 | configs/textdet/psenet/psenet\_resnet50\_fpnf\_600e\_icdar2015\_2gpu.py          |
-| psenet\_r50-oclip\_icdar2015.pth | PSENet + oCLIP       | ICDAR2015  |   520 | configs/textdet/psenet/psenet\_resnet50-oclip\_fpnf\_600e\_icdar2015\_2gpu.py    |
-| psenet\_mkv2vitae\_icdar2015.pth | PSENet + MonkeyOCRv2 | ICDAR2015  |   160 | configs/textdet/psenet/psenet\_mkv2vitae\_fpnf\_600e\_icdar2015\_4gpu\_adamw\.py |
-| dbnet\_r50\_icdar2015.pth        | DBNet baseline       | ICDAR2015  |   980 | configs/textdet/dbnet/dbnet\_resnet50\_1200e\_icdar2015\_2gpu.py                 |
-| dbnet\_r50-oclip\_icdar2015.pth  | DBNet + oCLIP        | ICDAR2015  |  1100 | configs/textdet/dbnet/dbnet\_resnet50-oclip\_1200e\_icdar2015\_2gpu.py           |
-| dbnet\_mkv2vitae\_icdar2015.pth  | DBNet + MonkeyOCRv2  | ICDAR2015  |   420 | configs/textdet/dbnet/dbnet\_mkv2vitae\_1200e\_icdar2015\_2gpu\_adamw\.py        |
-
 ## Environment
 
 The reproduced environment uses Python 3.11, PyTorch 2.9.0, CUDA 12.8,
@@ -185,7 +169,7 @@ python tools/test.py \
 # multi GPU
 bash tools/dist_test.sh \
   configs/textdet/psenet/psenet_mkv2vitae_fpnf_600e_ctw1500_4gpu_adamw.py \
-  model_weight/psenet_mkv2vitae_ctw1500.pth 1
+  model_weight/psenet_mkv2vitae_ctw1500.pth 4
 ```
 
 The evaluation prints `precision / recall / hmean` with the