Add DBNet++ RepViT pretrained weights

README.md

@@ -1,3 +1,69 @@
 ---
 license: apache-2.0
+tags:
+  - ocr
+  - text-detection
+  - dbnet
+  - pytorch
+library_name: ocrfactory
+pipeline_tag: object-detection
 ---
+
+# DBNet++ with RepViT Backbone
+
+A lightweight text detection model combining DBNet++ with RepViT backbone, optimized for efficient inference.
+
+## Model Description
+
+- **Architecture**: DBNet++ (Differentiable Binarization)
+- **Backbone**: RepViT (lightweight ViT-inspired CNN)
+- **Neck**: RSEFPN (Residual Squeeze-and-Excitation FPN)
+- **Head**: DBNetPPHead
+
+## Model Details
+
+| Component | Configuration |
+|-----------|--------------|
+| Backbone | RepViT |
+| Neck | RSEFPN (in: [48, 96, 192, 384], out: 96) |
+| Head | DBNetPPHead (inner: 24, k: 50) |
+| Parameters | ~3M |
+| Input Size | 640x640 (flexible) |
+
+## Usage
+
+```python
+import torch
+from ocrfactory.models.detect import DBNetPP
+
+# Build model
+model = DBNetPP(
+    backbone={"name": "RepViT"},
+    neck={"name": "RSEFPN", "in_channels": [48, 96, 192, 384], "out_channels": 96, "shortcut": True},
+    head={"name": "DBNetPPHead", "in_channels": 96, "inner_channels": 24, "k": 50, "use_asf": False}
+)
+
+# Load weights
+state_dict = torch.load("dbnetpp_repvit.pth", map_location="cpu")
+model.load_state_dict(state_dict, strict=True)
+model.eval()
+
+# Inference
+x = torch.randn(1, 3, 640, 640)
+with torch.no_grad():
+    output = model(x)
+    shrink_map = output["shrink_map"]  # (1, 1, 640, 640)
+```
+
+## Training
+
+This model was converted from [OpenOCR](https://github.com/Topdu/OpenOCR) pretrained weights trained on Chinese text detection datasets.
+
+## Original Source
+
+- OpenOCR: https://github.com/Topdu/OpenOCR
+- RepViT: https://github.com/THU-MIG/RepViT
+
+## License
+
+Apache 2.0

dbnetpp_repvit.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb34802356cc705bb22fe25c369071b3436de45f93c78adeedb9171fd998a01
+size 12728527