Skip to content

update dbnet README #113

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 28, 2023
Merged

update dbnet README #113

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 9 additions & 5 deletions configs/det/dbnet/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
English | [中文](https://github.com/mindspore-lab/mindocr/blob/main/configs/det/dbnet/README_CN.md)
English | [中文](README_CN.md)

# DBNet

Expand All @@ -18,7 +18,7 @@ into the architecture. DB simplifies post-processing and enhances the performanc
removed in the inference stage without sacrificing performance.[[1](#references)]

![dbnet_architecture](https://user-images.githubusercontent.com/16683750/225589619-d50c506c-e903-4f59-a316-8b62586c73a9.png)
<p style="text-align: center;"><em>Figure 1. Overall DBNet architecture</em></p>
<p align="center"><em>Figure 1. Overall DBNet architecture</em></p>

The overall architecture of DBNet is presented in _Figure 1._ It consists of multiple stages:

Expand All @@ -35,10 +35,14 @@ The overall architecture of DBNet is presented in _Figure 1._ It consists of mul
## Results

### ICDAR2015
<div align="center">

| **Model** | **Backbone** | **Pretrained** | **Recall** | **Precision** | **F-score** | **Recipe** | **Download** |
|-----------|--------------|----------------|------------|---------------|-------------|--------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------|
| DBNet | ResNet-50 | ImageNet | 81.70% | 85.84% | 83.72% | [yaml](https://github.com/mindspore-lab/mindocr/blob/main/configs/det/dbnet/db_r50_icdar15.yaml) | [weights](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-db1df47a.ckpt) |
| **Model** | **Backbone** | **Pretrained** | **Recall** | **Precision** | **F-score** | **Recipe** | **Download** |
|------------------|--------------|----------------|------------|---------------|-------------|-----------------------------|----------------------------------------------------------------------------------------------|
| DBNet (ours) | ResNet-50 | ImageNet | 81.70% | 85.84% | 83.72% | [yaml](db_r50_icdar15.yaml) | [weights](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-db1df47a.ckpt) |
| DBNet (PaddleOCR)| ResNet50_vd | SynthText | 78.72% | 86.41% | 82.38% |

</div>

## Quick Start

Expand Down
13 changes: 8 additions & 5 deletions configs/det/dbnet/README_CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
[English](https://github.com/mindspore-lab/mindocr/blob/main/configs/det/dbnet/README.md) | 中文
[English](README.md) | 中文

# DBNet

Expand All @@ -13,7 +13,7 @@ DBNet是一种基于分割的场景文本检测算法。在场景文本检测中
为了避免上述问题，DBNet在网络架构中集成了一个叫作“可微分二值化（Differentiable Binarization）”的自适应阈值。可微分二值化简化了后处理过程，增强了文本检测的性能。此外，在推理阶段移除该部分不会使性能降低[[1](#references)]。

![dbnet_architecture](https://user-images.githubusercontent.com/16683750/225589619-d50c506c-e903-4f59-a316-8b62586c73a9.png)
<p style="text-align: center;"><em>图 1. DBNet整体架构图</em></p>
<p align="center"><em>图 1. DBNet整体架构图</em></p>

DBNet的整体架构图如图1所示，包含以下阶段:

Expand All @@ -26,11 +26,14 @@ DBNet的整体架构图如图1所示，包含以下阶段:
## 实验结果

### ICDAR2015
<div align="center">

| **模型** | **骨干网络** | **预训练数据集** | **Recall** | **Precision** | **F-score** | **配置文件** | **模型权重下载** |
|------------------|------------|----------------|------------|---------------|-------------|-------------------------------|----------------------------------------------------------------------------------------------|
| DBNet (ours) | ResNet-50 | ImageNet | 81.70% | 85.84% | 83.72% | [yaml](db_r50_icdar15.yaml) | [weights](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-db1df47a.ckpt) |
| DBNet (PaddleOCR)| ResNet50_vd | SynthText | 78.72% | 86.41% | 82.38% |

| **模型** | **骨干网络** | **预训练数据集** | **Recall** | **Precision** | **F-score** | **配置文件** | **模型权重下载** |
|---------|------------|----------------|------------|---------------|-------------|-----------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------|
| DBNet | ResNet-50 | ImageNet | 81.70% | 85.84% | 83.72% | [yaml](https://github.com/mindspore-lab/mindocr/blob/main/configs/det/dbnet/db_r50_icdar15.yaml) | [weights](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-db1df47a.ckpt) |
</div>

## 快速上手

Expand Down
2 changes: 1 addition & 1 deletion configs/det/dbnet/db_r50_icdar15.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ train:
num_workers: 8

eval:
ckpt_load_path: ''
ckpt_load_path: 'tmp_det/best.ckpt'
dataset_sink_mode: False
dataset:
type: DetDataset
Expand Down