ModelPrésentéExterne

Dbnetpp Repvit Ch

Lightweight text detection model combining DBNet++ with RepViT backbone, optimized for efficient inference. Pretrained on Chinese text detection datasets.

Sourcehuggingface.co/indicnode/dbnetpp_repvit_ch/tree/191d8c6ce2172cbcd75856b3e3b57e9ea6262b4e

TypeOtherVersionRevision 191d8c6CClasse

Source du modèle

Type: Other
Taille du fichier: 12,1 MB
Version: vRevision 191d8c6
Mis à jour: 16 sept. 2026
Téléchargements: 0
Source: Hugging Face

Description de la source

DBNet++ RepViT (Chinese)

Lightweight text detection model combining DBNet++ with RepViT backbone, optimized for efficient inference. Pretrained on Chinese text detection datasets.

Model Details

Component	Configuration
Architecture	DBNet++ (Differentiable Binarization)
Backbone	RepViT (lightweight ViT-inspired CNN)
Neck	RSEFPN (in: [48, 96, 192, 384], out: 96)
Head	DBNetPPHead (inner: 24, k: 50)
Parameters	~3M
Input Size	640x640 (flexible)

Training Data

This model was converted from OpenOCR pretrained weights, trained on Chinese text detection datasets.

Recommended datasets for fine-tuning:

MSRA-TD500 (Chinese + English)
ICDAR2017 RCTW (Chinese)
CTW1500

Note: For English-only text detection, fine-tuning on English datasets (ICDAR2015, Total-Text) is recommended.

Usage

With Hugging Face

from huggingface_hub import hf_hub_download
import torch

# Download model
model_path = hf_hub_download(
    repo_id="thisisiron/dbnetpp_repvit_ch",
    filename="dbnetpp_repvit_ch.pth"
)

# Load weights
state_dict = torch.load(model_path, map_location="cpu")

With OCR-Factory

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_ch.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 Config (YAML)

architecture:
  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

Performance

Dataset	Precision	Recall	H-mean
MSRA-TD500	-	-	-

Performance metrics will be updated after benchmarking.

References

OpenOCR: https://github.com/Topdu/OpenOCR
RepViT: https://github.com/THU-MIG/RepViT
DBNet++: Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion

License

Apache 2.0

Sources

1 source

Hugging FacePrincipalVersion 191d8c6ce2172cbcd75856b3e3b57e9ea6262b4e

huggingface.co/indicnode/dbnetpp_repvit_ch/tree/191d8c6ce2172cbcd75856b3e3b57e9ea6262b4e

Vérifié 1 sept.

Artefacts du modèle

1 artefact

dbnetpp_repvit_ch.pth

pth · 12,1 MB · SHA-256 abb34802356c…8a01 · Hugging Face

Download file

Extraits de sources

2 extraits

Readme1 sept.huggingface.co/indicnode/dbnetpp_repvit_ch

--- license: apache-2.0 language: - zh - en tags: - text-detection - ocr - dbnet - repvit - pytorch datasets: - chinese-text-detection pipeline_tag: image-segmentation --- # DBNet++ RepViT (Chinese) Lightweight text detection model combining DBNet++ with RepViT backbone, optimized for efficient inference. Pretrained on **Chinese text detection datasets**. ## Model Details | Component | Configuration | |-----------|--------------| | Architecture | DBNet++ (Differentiable Binarization) | | Backbone | RepViT (lightweight ViT-inspired CNN) | | Neck | RSEFPN (in: [48, 96, 192, 384], out: 96) | | Head | DBNetPPHead (inner: 24, k: 50) | | Parameters | ~3M | | Input Size | 640x640 (flexible) | ## Training Data This model was converted from [OpenOCR](https://github.com/Topdu/OpenOCR) pretrained weights, trained on **Chinese text detection datasets**. **Recommended datasets for fine-tuning:** - MSRA-TD500 (Chinese + English) - ICDAR2017 RCTW (Chinese) - CTW1500 **Note:** For English-only text detection, fine-tuning on English datasets (ICDAR2015, Total-Text) is recommended. ## Usage ### With Hugging Face ```python from huggingface_hub import hf_hub_download import torch # Download model model_path = hf_hub_download( repo_id="thisisiron/dbnetpp_repvit_ch", filename="dbnetpp_repvit_ch.pth" ) # Load weights state_dict = torch.load(model_path, map_location="cpu") ``` ### With OCR-Factory ```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_ch.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 Config (YAML) ```yaml architecture: 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 ``` ## Performance | Dataset | Precision | Recall | H-mean | |---------|-----------|--------|-----...

Note1 sept.huggingface.co/indicnode/dbnetpp_repvit_ch

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Repo indicnode/dbnetpp_repvit_ch