config.enable_memory_optim() 这一行开启后，启动报错，去掉就整正常

[yangy996]

🔎 Search before asking

• I have searched the PaddleOCR Docs and found no similar bug report.
• I have searched the PaddleOCR Issues and found no similar bug report.
• I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

config.enable_memory_optim() 出现如下错误：
ocr/tools/infer/utility.py", line 289, in create_predictor
predictor = inference.create_predictor(config)
ValueError: (InvalidArgument) Not find predictor_id 0 and pass_name memory_optimize_pass
[Hint: Expected map.count(predictor_id) && map[predictor_id].count(pass_name) == true, but received map.count(predictor_id) && map[predictor_id].count(pass_name):0 != true:1.] (at /paddle/paddle/fluid/inference/analysis/pass_result_info.h:54)

🏃‍♂️ Environment (运行环境)

uname -a
Linux localhost.localdomain 5.10.0-284.0.0.187.oe2203sp4.aarch64 #1 SMP Thu Oct 9 15:18:13 CST 2025 aarch64 aarch64 aarch64 GNU/Linux

版本：
paddlepaddle 3.1.0

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

调用的代码，但通过paddleocr命令去调用，没这个错误
paddleocr ocr -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False
这个调用就正常

[yuanlehome]

这个报错可以忽略。paddle3.0之后，默认使用pir推理，这个api不起作用了，后续我们会判断下，pir下调用这个api什么也不用做即可，这里给出报错有点不友好～