-
Notifications
You must be signed in to change notification settings - Fork 57
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.
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
基于MindOCR的车牌识别 #760
基于MindOCR的车牌识别 #760
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
建议修订部分内容
已按照批注修改 |
examples/license_plate_detection_and_recognition/generate_dict.py |
是的,您是正确的。这应该是之前为了统计合并后的字符数加上去的,应该去掉。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
-
文档有新要求,麻烦统一按照该样例整理中英文文档的环境信息,性能表现 https://github.com/mindspore-lab/mindone/wiki/%E6%A8%A1%E5%9E%8B%E7%89%88%E6%9C%AC%E4%B9%A6%E5%86%99%E6%A0%B7%E4%BE%8B
-
数据集地址直接放官方链接,避免填写网盘地址
老师,我这用GPU训的没有ascend+cann的版本信息,我写GPU dirver和GPU型号,以及cudatoolkit版本可以不 |
1.已添加环境信息和性能表现,请导师审核 |
已按照检视要求修改 |
|
已按照检视要求修改,请导师审核 |
潘导您好!
已按照所提修改意见对文档进行修改,请审核!
…------------------ 原始邮件 ------------------
发件人: "mindspore-lab/mindocr" ***@***.***>;
发送时间: 2024年11月15日(星期五) 晚上8:43
***@***.***>;
***@***.******@***.***>;
主题: Re: [mindspore-lab/mindocr] 基于MindOCR的车牌识别 (PR #760)
文档有新要求,麻烦统一按照该样例整理中英文文档的环境信息,性能表现 https://github.com/mindspore-lab/mindone/wiki/%E6%A8%A1%E5%9E%8B%E7%89%88%E6%9C%AC%E4%B9%A6%E5%86%99%E6%A0%B7%E4%BE%8B
数据集地址直接放官方链接,避免填写网盘地址
1.已添加环境信息和性能表现,请导师审核 2.数据集论文作者只提供了百度网盘的地址和谷歌网盘的地址
此处的建议,是直接提供数据集官方github链接,并告诉用户,按照官方github项目链接的指引进行下载,而不是绕过其链接,直接贴百度网盘和GoogleDrive地址。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
@Xv-M-S 你好,请注意上面还有4个处于“pending”状态的review意见。已经当面请第二位reviewer @chengtianwu 补充检视和合入PR了。 |
潘导您好!1. ”pending“状态的review意见都在最新提交的pr里解决了,没有及时点击resolve;
2. 对于配图可能产生误导的问题,现在已经将相关配图删除,并提供了mindpsore安装官网,提示用户到官网选择和自己环境相适配的安装包,并相应修改了其他一些可能误导的表述
请审核
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2024年11月21日(星期四) 中午11:37
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [mindspore-lab/mindocr] 基于MindOCR的车牌识别 (PR #760)
潘导您好! 已按照所提修改意见对文档进行修改,请审核!
@Xv-M-S 你好,请注意上面还有4个处于“pending”状态的review意见。已经当面请第二位reviewer @chengtianwu 补充检视和合入PR了。
请重点关注,当前文档中配图为安装GPU版本的MindSpore,但是提供的环境配套信息和测试数据都是NPU版本(上次修改删去了GPU相关信息),可能会误导用户。建议参考review意见调整下中英文档。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
潘导您好!
1. 已添加GPU的环境信息和测试信息
2. 已根据检视要求修改相关表述
请审核
…------------------ 原始邮件 ------------------
发件人: "mindspore-lab/mindocr" ***@***.***>;
发送时间: 2024年11月21日(星期四) 晚上6:00
***@***.***>;
***@***.******@***.***>;
主题: Re: [mindspore-lab/mindocr] 基于MindOCR的车牌识别 (PR #760)
@panshaowu approved this pull request.
In examples/license_plate_detection_and_recognition/README_CN.md:
> @@ -72,9 +71,9 @@ ads = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q' ## 环境要求 -硬件平台:Ascend、GPU - -软件平台:MindSpore 2.2.14 +|mindspore|ascend driver|firmware|cann toolkit/kernel|
如果readme中完全删掉了GPU的环境信息和性能测试数据,则在“安装环境依赖->安装MindSpore 2.2.14”章节,不应配一张GPU的图,并写“选择mindspore的版本为2.2.14,以及适配的CUDA版本获取安装命令”。这样容易误导用户。
考虑到文档中已经写了支持GPU或Ascend NPU,建议同时列出NPU和GPU的环境信息和性能测试数据(2组表格)
“安装环境依赖->安装MindSpore 2.2.14”章节,调整措辞,例如“按照MindSpore官网指引,安装MindSpore 2.2.14版本及其配套的GPU或昇腾AI处理器配套软件包”。
注意:上述修改设计中英文文档多处。
In examples/license_plate_detection_and_recognition/README_CN.md:
> @@ -12,10 +14,7 @@ ## 数据集下载 -从Google云盘中或百度网盘中下载数据集: - -* [Google Drive](https://drive.google.com/open?id=1rdEsCUcIUaYOVRkx5IMTRNA7PcGMmSgc) -* [BaiduYun Drive(code: hm0u)](https://pan.baidu.com/s/1i5AOjAbtkwb17Zy-NQGqkw) +在[CCPD官方项目网址](https://github.com/detectRecog/CCPD)中,按照指引下载数据集:
建议:
“按照CCPD官方项目网址的指引,下载数据集:”
In examples/license_plate_detection_and_recognition/README.md:
> + +# License plate recognition based on MindOCR + +# Dataset processing + +## Dataset introduction + +Due to the lack of publicly available large and diverse datasets, most current license plate detection and recognition methods are evaluated on small and often unrepresentative datasets. This paper propose a large and comprehensive license plate dataset, CCPD, where all images are manually captured and carefully annotated by workers from a roadside parking management company. CCPD is the largest publicly available license plate dataset to date, with more than 250,000 unique car images, and the only dataset that provides vertex position annotations. + +Paper: [Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline](https://openaccess.thecvf.com/content_ECCV_2018/papers/Zhenbo_Xu_Towards_End-to-End_License_ECCV_2018_paper.pdf) + +Code repository: [https://github.com/detectRecog/CCPD](https://github.com/detectRecog/CCPD) + +## Dataset download + +On the [CCPD official project website](https://github.com/detectRecog/CCPD), follow the instructions to download the dataset:
建议:
Download the dataset following the instructions on the CCPD official project website:
In examples/license_plate_detection_and_recognition/README_CN.md:
> @@ -145,7 +144,12 @@ make 根据对应关系表,应该下载0.3版本的。
建议(原句存在语义含糊):
根据MindSpore和MindOCR的版本配套关系,下载安装0.3版本的MindOCR。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
@@ -414,7 +418,7 @@ valid res: | |||
[2024-09-10 23:01:26] mindocr.eval INFO - Performance: {'acc': 0.9795991778373718, 'norm_edit_distance': 0.995379626750946} | |||
``` | |||
|
|||
6. 修改`SVTRRecAug`的`aug_type`为1:应用更强的数据集增强方式。[svtr_transform.py](https://github.com/mindspore-lab/mindocr/blob/5fd78b46b42d40aeba01f72538699837594053b1/mindocr/data/transforms/svtr_transform.py#L354) | |||
6. 增加数据增强强度:将配置文件`SVTRRecAug`部分的`aug_type`修改为1 | |||
|
|||
```java |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
java -> text
@@ -396,7 +400,7 @@ valid res: | |||
[2024-09-10 19:14:02] mindocr.eval INFO - Performance: {'acc': 0.069402776658535, 'norm_edit_distance': 0.765773355960846} | |||
``` | |||
|
|||
4. Resize策略:不考虑宽高比,直接将所有文本图像`resize`到`32 * 100`,`Resize`时不使用`Padding` ; `max_text_length: 25` | |||
4. Resize策略: 直接将所有文本图像`resize`到`32 * 100`,`Resize`时不使用`Padding`;`max_text_length`设置为25; | |||
|
|||
```java |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
java -> text
|
||
```java | ||
valid res: | ||
[2024-09-10 15:16:38] mindocr.metrics.rec_metrics INFO - correct num: 23, total num: 99996.0 | ||
[2024-09-10 15:16:38] mindocr.eval INFO - Performance: {'acc': 0.00023000920191407204, 'norm_edit_distance': 0.5451045036315918} | ||
``` | ||
|
||
3. 将`image_shape`调整为【32,80】等比例放缩 | ||
3. 修改配置文件`model`部分的`img_size`为[32,80] | ||
|
||
```java |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
java -> text
├── images | ||
│ ├── img_1.jpg | ||
│ ├── img_2.jpg | ||
│ └── ....jpg |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
....jpg -> ...
潘导您好!
PR已经合入的话,麻烦在任务链接 https://gitee.com/mindspore/community/issues/I98K8W#note_33417674 结束一下任务,我得实习期也快到了。
…------------------ 原始邮件 ------------------
发件人: "mindspore-lab/mindocr" ***@***.***>;
发送时间: 2024年11月22日(星期五) 上午9:56
***@***.***>;
***@***.******@***.***>;
主题: Re: [mindspore-lab/mindocr] 基于MindOCR的车牌识别 (PR #760)
Merged #760 into main.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Thank you for your contribution to the MindOCR repo.
Before submitting this PR, please make sure:
Motivation
【开源实习】基于MindOCR的车牌识别案例输出 (https://gitee.com/mindspore/community/issues/I98K8W)
为基于MindOCR的车牌号识别案例提供英文readme
Test Plan
(How should this PR be tested? Do you require special setup to run the test or repro the fixed bug?)
Related Issues and PRs
【开源实习】基于MindOCR的车牌识别案例输出 (https://gitee.com/mindspore/community/issues/I98K8W)
(Is this PR part of a group of changes? Link the other relevant PRs and Issues here. Use https://help.github.com/en/articles/closing-issues-using-keywords for help on GitHub syntax)