PP-OCR v4 推理模型导出不可用

[jinxiqinghuan]

按照官方模型，使用官方配置文件，对训练模型进行转换后，发现模型不可用。
使用评估代码eval.py报错如下：

W0914 09:11:10.831167 130074 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 7.5, Driver API Version: 11.6, Runtime API Version: 11.6
W0914 09:11:10.832507 130074 gpu_resources.cc:91] device: 0, cuDNN Version: 8.8.
[2023/09/14 09:11:13] ppocr INFO: load pretrain successful from ./model/rec/ch_PP-OCRv4_rec_server_infer/best_accuracy
[2023/09/14 09:11:17] ppocr INFO: inference model is saved to /data/experiment/ocr/text/inference/rec/rec_v4_real_2/inference
(doc-ocr) [ljt@gpu131 text]$ sudo bash eval.sh 
[2023/09/14 09:12:09] ppocr INFO: In PP-OCRv3, rec_image_shape parameter defaults to '3, 48, 320', if you are using recognition model with PP-OCRv2 or an older version, please set --rec_image_shape='3,32,320
[2023/09/14 09:12:12] ppocr INFO: Traceback (most recent call last):
  File "PaddleOCR/tools/infer/predict_rec.py", line 662, in main
    rec_res, _ = text_recognizer(img_list)
  File "PaddleOCR/tools/infer/predict_rec.py", line 616, in __call__
    self.predictor.run()
OSError: (External) CUDNN error(9), CUDNN_STATUS_NOT_SUPPORTED. 
  [Hint: Please search for the error code(9) on website (https://docs.nvidia.com/deeplearning/cudnn/api/index.html#cudnnStatus_t) to get Nvidia's official solution and advice about CUDNN Error.] (at /paddle/paddle/fluid/operators/fused/conv_fusion_op.cu:519)
  [operator < conv2d_fusion > error]

[2023/09/14 09:12:12] ppocr INFO: (External) CUDNN error(9), CUDNN_STATUS_NOT_SUPPORTED. 
  [Hint: Please search for the error code(9) on website (https://docs.nvidia.com/deeplearning/cudnn/api/index.html#cudnnStatus_t) to get Nvidia's official solution and advice about CUDNN Error.] (at /paddle/paddle/fluid/operators/fused/conv_fusion_op.cu:519)
  [operator < conv2d_fusion > error]

将其转为frpc的server模型后，接口也会报错无法运行。
更换环境也无法解决，转换导出过程都不报错，但是模型就是不可用。
希望尽快解决这个问题，谢谢！！！

[SWHL]

可以参考RapidOCR