You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+40-31Lines changed: 40 additions & 31 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,22 +15,22 @@ English | [中文](README_CN.md)
15
15
[Introduction](#introduction) |
16
16
[Installation](#installation) |
17
17
[Quick Start](#quick-start) |
18
-
[Model List](#supported-models-and-performance) |
18
+
[Model List](#model-list) |
19
19
[Notes](#notes)
20
20
21
21
</div>
22
22
23
23
24
24
## Introduction
25
-
MindOCR is an open-source toolbox for OCR development and application based on [MindSpore](https://www.mindspore.cn/en). It helps users to train and apply the best text detection and recognition models, such as DBNet/DBNet++ and CRNN/SVTR, to fulfuill image-text understanding need.
25
+
MindOCR is an open-source toolbox for OCR development and application based on [MindSpore](https://www.mindspore.cn/en). It helps users to train and apply the best text detection and recognition models, such as DBNet/DBNet++ and CRNN/SVTR, to fulfill image-text understanding needs.
26
26
27
27
28
28
<detailsopen>
29
29
<summary> Major Features </summary>
30
30
31
-
-**Modulation design**: We decouple the ocr task into serveral configurable modules. Users can setup the training and evaluation pipeline easily for customized data and models with a few line of modification.
31
+
-**Modulation design**: We decouple the OCR task into several configurable modules. Users can set up the training and evaluation pipeline easily for customized data and models with a few lines of modification.
32
32
-**High-performance**: MindOCR provides pretrained weights and the used training recipes that reach competitive performance on OCR tasks.
33
-
-**Low-cost-to-apply**: We provide easy-to-use inference tools to perform text detection and recogintion tasks.
33
+
-**Low-cost-to-apply**: We provide easy-to-use inference tools to perform text detection and recognition tasks.
34
34
</details>
35
35
36
36
@@ -43,7 +43,7 @@ To install the dependency, please run
43
43
pip install -r requirements.txt
44
44
```
45
45
46
-
Additionally, please install MindSpore(>=1.9) following the official [instructions](https://www.mindspore.cn/install) for the best fit of your machine.
46
+
Additionally, please install MindSpore(>=1.9) following the official [installation instructions](https://www.mindspore.cn/install) for the best fit of your machine.
47
47
48
48
For distributed training, please install [openmpi 4.0.3](https://www.open-mpi.org/software/ompi/v4.0/).
We will use **DBNet** model and **ICDAR2015** dataset for demonstration, although other models and datasets are also supported. Please refer to [DBNet model README](configs/det/dbnet/README.md).
68
+
#### 1.1 Text Detection
69
69
70
+
We will take **DBNet** model and **ICDAR2015** dataset as an example to illustrate how to configure the training process with a few lines of modification on the yaml file.
70
71
71
-
### Text Recognition Model Training
72
+
Please refer to [DBNet readme](configs/det/dbnet/README.md#3-quick-start) for detailed instructions.
72
73
73
-
We will use **CRNN** model and **LMDB** dataset for demonstration, although other models and datasets are also supported. Please refer to [CRNN model README](configs/rec/crnn/README.md).
74
74
75
+
#### 1.2 Text Recognition
75
76
76
-
### Inference and Deployment
77
+
We will take **CRNN** model and **LMDB** dataset as an illustration on how to configure and launch the training process easily.
77
78
78
-
#### Inference with MX Engine
79
+
Detailed instructions can be viewed in [CRNN readme](configs/rec/crnn/README.md#3-quick-start).
79
80
80
-
Please refer to [mx_infer](docs/cn/inference_cn.md).
81
+
**Note:**
82
+
The training pipeline is fully extendable. To train other text detection/recognition models on a new dataset, please configure the model architecture (backbone, neck, head) and data pipeline in the yaml file and launch the training script with `python tools/train.py -c /path/to/yaml_config`.
81
83
82
-
#### Inference with Lite
84
+
###2. Inference and Deployment
83
85
84
-
Coming soon
86
+
#### 2.1 Inference with MX Engine
87
+
88
+
MX, which is short for [MindX](https://www.hiascend.com/zh/software/mindx-sdk), allows efficient model inference and deployment on Ascend devices.
85
89
86
-
#### Inference with native MindSpore
90
+
MindOCR supports OCR model inference with MX Engine. Please refer to [mx_infer](docs/cn/inference_cn.md) for detailed illustrations.
91
+
92
+
#### 2.2 Inference with MS Lite
87
93
88
94
Coming soon
89
95
90
-
## Supported Models and Performance
96
+
#### 2.3 Inference with native MindSpore
97
+
98
+
Coming soon
91
99
92
-
### Text Detection
100
+
##Model List
93
101
94
-
The supported detection models and their performance on the test set of ICDAR2015 are as follow.
The supported recognition models and their overall performance on the public benchmarking datasets (IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) are as follow
For the detailed performance of the trained models, please refer to [configs](./configs).
111
120
112
-
For more details, please refer to [configs](./configs).
121
+
For detailed inference performance using MX engine, please refer to [mx inference performance](docs/cn/inference_models_cn.md)
113
122
114
123
## Notes
115
124
116
125
### Change Log
117
126
- 2023/03/23
118
-
1. Add dynamic loss scaler support, compatiable with drop overflow update. To enable dynamic loss scaler, please set `type` of `loss_scale` as `dynamic`. A yaml example can be viewed in `configs/rec/crnn/crnn_icdar15.yaml`
127
+
1. Add dynamic loss scaler support, compatible with drop overflow update. To enable dynamic loss scaler, please set `type` of `loss_scale` as `dynamic`. A YAML example can be viewed in `configs/rec/crnn/crnn_icdar15.yaml`
@@ -139,7 +148,7 @@ For more details, please refer to [configs](./configs).
139
148
140
149
### How to Contribute
141
150
142
-
We appreciate all kind of contributions including issues and PRs to make MindOCR better.
151
+
We appreciate all kinds of contributions including issues and PRs to make MindOCR better.
143
152
144
153
Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for the contributing guideline. Please follow the [Model Template and Guideline](mindocr/models/README.md) for contributing a model that fits the overall interface :)
0 commit comments