search

peakhell / OCRIntegrator

OCRFusion is an integrated solution that combines multiple open-source OCR (Optical Character Recognition) models, layout analysis, and table parsing capabilities. This project unifies these functionalities into a single interface, providing a streamlined and efficient way to process and extract information from various types of documents.
Apache License 2.0
11 stars 1 forks source link

请问可以提供一下运行环境吗？ #1

Open PureWaterCatt opened 3 months ago

PureWaterCatt commented 3 months ago

RT，我在跑trt模型的时候提示不兼容，需要rebuild，可以的话可以告知一下运行的环境吗？

peakhell commented 3 months ago

I update my readme、gpu environment and setup step, now you can follow the step to run this project.

PureWaterCatt commented 3 months ago

I update my readme、gpu environment and setup step, now you can follow the step to run this project.

Thank you so much for the readme. I tried to run the project and managed to get some output from the pdf file. However, I am in some trouble with a pdf of an image that I wasn't able to run successfully, but that's where running the onnx model with the CPU gets me normal results.

Output: [06/27/2024-02:51:33] [TRT] [E] 3: [executionContext.cpp::setInputShape::2068] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::setInputShape::2068, condition: satisfyProfile Runtime dimension does not satisfy any optimization profile.) [06/27/2024-02:51:34] [TRT] [E] 3: [executionContext.cpp::resolveSlots::2842] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::resolveSlots::2842, condition: allInputDimensionsSpecified(routine) )

I need help if possible, this is my pdf file that you can try. Thank you again. test.pdf

peakhell commented 3 months ago

I update my readme、gpu environment and setup step, now you can follow the step to run this project.

Thank you so much for the readme. I tried to run the project and managed to get some output from the pdf file. However, I am in some trouble with a pdf of an image that I wasn't able to run successfully, but that's where running the onnx model with the CPU gets me normal results.

Output: [06/27/2024-02:51:33] [TRT] [E] 3: [executionContext.cpp::setInputShape::2068] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::setInputShape::2068, condition: satisfyProfile Runtime dimension does not satisfy any optimization profile.) [06/27/2024-02:51:34] [TRT] [E] 3: [executionContext.cpp::resolveSlots::2842] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::resolveSlots::2842, condition: allInputDimensionsSpecified(routine) )

I need help if possible, this is my pdf file that you can try. Thank you again. test.pdf

pull this repo and try again. When converting the model to TRT, you need to specify the minimum dimensions. I lowered this minimum dimension, which should solve the problem.