PaddleOCR/main/version3.x/module_usage/text_recognition #15474
Replies: 52 comments 72 replies
-
|
请问模型微调导出后如何使用 |
Beta Was this translation helpful? Give feedback.
-
|
请问,蒸馏模型模型如何导出呢,导出后yml文件不存在Global模型名称,paddleocr3.0找不到模型名称对应问题,包括老师模型都不存在 |
Beta Was this translation helpful? Give feedback.
-
|
导出后添加,会报错,
…---- Replied Message ----
| From | ***@***.***> |
| Date | 05/29/2025 下午7:56 |
| To | PaddlePaddle/PaddleOCR ***@***.***> |
| Cc | SHOUshou0426 ***@***.***>,
Comment ***@***.***> |
| Subject | Re: [PaddlePaddle/PaddleOCR] PaddleOCR/main/version3.x/module_usage/text_recognition (Discussion #15474) |
或者直接在导出后的inference.yaml 里加上也可以
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
错误大概就是找不到模型名称,信息我是直接复制的config内的配置文件,比如en_ppocrv2_cml
…---- Replied Message ----
| From | ***@***.***> |
| Date | 05/29/2025 下午8:06 |
| To | PaddlePaddle/PaddleOCR ***@***.***> |
| Cc | SHOUshou0426 ***@***.***>,
Comment ***@***.***> |
| Subject | Re: [PaddlePaddle/PaddleOCR] PaddleOCR/main/version3.x/module_usage/text_recognition (Discussion #15474) |
具体是什么错误呢?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
我是用的是这个配置文件,进行蒸馏训练ch_PP-OCRv3_det_cml.yml
训练的时候才用的是paddle2.4版本的环境,然后发现最版本导出不了,则更新到最新的paddle 版本然后到处后没有Global 模型名称,我就将ch_PP-OCRv3_det_cml作为名称添加进行,丢错还是找不到模型名称
在 2025-05-29 20:06:47,"liuhongen1234567" ***@***.***> 写道:
具体是什么错误呢?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
目前还有个问题就是,才用旧版本的paddlepaddle 训练的ppocrv3 的英文rec 模型,在使用最新的paddle 环境导出模型,发现效果差到极点,环境版本不一致,会出现这种问题吗,还是说我用最新版本的paddle 训练ocrv5 就不会出现这个问题呢
在 2025-05-29 20:06:47,"liuhongen1234567" ***@***.***> 写道:
具体是什么错误呢?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
比如我训练pcb 的文字识别,大概有1300张左右数据英文的有必要增加v5的预训练模型吗,因为英文版的v5 rec 发现字典是中英混合的
在 2025-05-29 20:29:11,"liuhongen1234567" ***@***.***> 写道:
训练和推理时的paddle版本尽量保持一致吧。从2.4到3.0跨度有点大,可能有些算子不一样了,用最新版的paddle训练ocrv5一般不会出现问题。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
我的问题和他很像,你可以看一下他的问题,我就知道如何解决了,
在 2025-05-29 20:26:09,"liuhongen1234567" ***@***.***> 写道:
您找,目前这个模型名称要从文本检测模型列表里选择,可以把模型名称设置成PP-OCRv4_mobile_det 试试呢?
image.png (view on web)
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
但是增加了预训练模型,我发现,v3的检测模型我才用了预训练模型,测试结果发现,他会多检测一些文字,但是大多数都是根据我标注的数据集的格式相似,10%是会出现多检测,和一个字母检测2-3遍,导致识别模型出现误检
在 2025-05-29 20:49:45,"liuhongen1234567" ***@***.***> 写道:
在很多文档场景中,中英文都是混合的,因此v5进行了一定程度的大一统,试图一个模型解决中英繁日拼音的识别。v5其实模型上没有太大的改进,主要在训练数据集上,如果是英文的话我这边更建议用v3或v4的英文模型,1300张要从头训练应该是远远不够的。一般学术界的识别模型,都要在80甚至100w上进行预训练
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
paddleocr 的数据是否有增广方式呢,比如目标检测那种可以离线增广,扩充数据集的
在 2025-05-29 20:59:10,"liuhongen1234567" ***@***.***> 写道:
好的,看起来您的场景比较垂类,可以多做几组实验看看吧。可能在您的场景里不加入预训练会更好一些
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
是否有相关的ocr 离线增广的相关demo呢或者资料
在 2025-05-29 20:59:10,"liuhongen1234567" ***@***.***> 写道:
好的,看起来您的场景比较垂类,可以多做几组实验看看吧。可能在您的场景里不加入预训练会更好一些
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
您好,这边还有个问题,训练PPOCR det 模型,模型input的size 从最初配置文件960更改为224,训练完成,使用官方给出的python 代码需要指定input_size 吗,还是说text_det_limit_side_len要指定为224
在 2025-05-29 20:59:10,"liuhongen1234567" ***@***.***> 写道:
好的,看起来您的场景比较垂类,可以多做几组实验看看吧。可能在您的场景里不加入预训练会更好一些
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
老师你好,请问微调时数据量比较小(一千多张训练图片),怎么冻结前面层,只训练后面几层?在哪里可以进行配置 |
Beta Was this translation helpful? Give feedback.
-
|
您好,请问识别图片中多行文字失效应该如何解决 |
Beta Was this translation helpful? Give feedback.
-
|
您好,PPOCRV5提出的实例代码,显示支持tensorrt ,我使用trt 推理则显示trt8的一些操作缺少AttributeError: 'tensorrt.tensorrt.IBuilderConfig' object has no attribute 'set_memory_pool_limit'
环境:
CUDA:11.2
CUDNN:8.4.1.50
TensorRT:8.0.1.6
trt 官方的samples 是没有问题的可以正常测试
以下是trt 报错,并且中间打印了一些关于算子的东西,我不确定是不是算子也有问题,下面是我的ocr实例代码里面展现了使用的模型
在 2025-06-03 17:27:57,"liuhongen1234567" ***@***.***> 写道:
您好, /usr/local/lib/python3.10/dist-packages/paddlex/inference/models/text_detection/processors.py 中的 DBPostProcess 有一个检测框过滤的操作,不知道是不是您所需要的。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.
在 2025-06-04 17:00:20,"liuhongen1234567" ***@***.***> 写道:
您好,多行文本建议直接使用PP-OCRv5 产线 https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/pipeline_usage/OCR.html,先进行检测再进行识别。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
请问一下我报错FileNotFoundError: [Errno 2] No such file or directory: './train_data/train_list.txt'是什么情况呢,我下载的ocr_rec_dataset_examples.tar里面也没有这个文件呢。具体日志如下: |
Beta Was this translation helpful? Give feedback.
-
|
Beta Was this translation helpful? Give feedback.
-
|
现在OVRv5的识别模型,为何微调训练后的模型识别精度严重下降,之前可以识别的文本现在都会识别错误,是要进行什么冻结操作吗? Optimizer: Architecture:
Loss:
PostProcess: Metric: Train:
这是我现在的.yaml文件,现在微调是为了解决模型识别不到数字与字母之间空格的问题,训练后发现空格可以识别到了,但是现在模型检测识别原先的文本会出现很多错误。 |
Beta Was this translation helpful? Give feedback.
-
|
静态图模型可以直接集成到 PaddleOCR 的 API 中,这一步具体咱实现? |
Beta Was this translation helpful? Give feedback.
-
|
您好,我想对文本识别模型进行微调,目前的模型对我们专业的特殊符号识别不准。在构建数据集时,我是应该单独把这个特殊符号作为一个样本,还是这个特殊符号和临近正常的文本一起作为一个样本?另外,构建好样本后,是否应该对图形进行缩放、旋转等增强操作? |
Beta Was this translation helpful? Give feedback.
-
|
你好,请问ocr对数字的识别是以训练数据集里的数字为单位还是以单个数字为单位呢?我最近遇到一个问题:我的数据集都是两位数的数字,但是对数据集没有涉及的数字识别效果很差。举个例子:我的数据集里有“17”和“36”,用得到的模型识别“16”时,总是识别成17或36。如果是以训练数据集里的数字为单位的话,那是不是意味着我要在数据集里体现0-99的所有数字?我认为是不太合理的,如果是以单个数字为单位,那我所说的上述情况该怎么解决呢?谢谢您! |
Beta Was this translation helpful? Give feedback.
-
|
小白提问哈,预训练模型和推理模型能力有什么差别,要做微调,使用预训练是相当于重头训练吗?如果只是想补充样本少量样本训练会有效果吗?比如调一个证件识别,50到100个样本会有效果吗? |
Beta Was this translation helpful? Give feedback.
-
|
文本识别的微调是否需要提供大型数据集?我想要扩展字符集以提高对一些特殊符号的识别能力,下载训练模型后微调,精度难以上升,我猜测可能是数据量不足导致的(500左右)。 |
Beta Was this translation helpful? Give feedback.
-
|
我训练完成后导出模型有json、yml、pdiparams,然后我调用 初始化OCR时出错: Model name mismatch,please input the correct model dir. |
Beta Was this translation helpful? Give feedback.
-
|
大佬我请问一下,我要提高rec模型对于印章遮挡文字的识别效果,我是把印章遮挡数据加入通用数据一起训练呢,还是先用几百万的通用数据训练,再用印章遮挡数据训练呢 |
Beta Was this translation helpful? Give feedback.
-
|
请问一下,我希望在v5版本的识别模型基础上进行模型微调,我仿照官网准备了一些数据,我的显卡是rtx5070,我运行代码的时候use_gpu: false 是可以正常运行的,use_gpu: true就报错:RuntimeError: (PreconditionNotMet) warp-ctc [version 2] Error in get_workspace_size: execution failed |
Beta Was this translation helpful? Give feedback.
-
|
我二次训练了一个模型,但是训练之后的评估的结果很不好才 准确率才5%,我不知道是什么原因。 Global: Optimizer: Architecture: Loss: PostProcess: Metric: Train: Eval: 数据集的话需要我也可以提供 |
Beta Was this translation helpful? Give feedback.
-
|
你好,识别印章遮盖下的文字可以试用微调实现吗,提升识别准确率 |
Beta Was this translation helpful? Give feedback.
-
|
Successfully installed paddlex-3.3.0 (ppocr) E:\Train_251213\PaddleOCR-3.3.2>paddlex --paddle2onnx --opset_version 9 --paddle_model_dir ../export_tmp/ --onnx_model_dir ../onnxout |
Beta Was this translation helpful? Give feedback.
-
|
模型导出后inference结果错误:使用tools/export_model.py导出训练后的模型后,在PaddleOCR中使用,对相同的图片,inference结果错误。但是使用python tools/infer_rec.py进行推理,结果是正确的。请问可能是什么原因导致的? |
Beta Was this translation helpful? Give feedback.



Uh oh!
There was an error while loading. Please reload this page.
-
PaddleOCR/main/version3.x/module_usage/text_recognition
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
https://paddlepaddle.github.io/PaddleOCR/main/version3.x/module_usage/text_recognition.html
Beta Was this translation helpful? Give feedback.
All reactions