error loading custom trained detection model after conversion (detection)

[Zenmaster188]

I trained the Paddle detection model with my own custom data, and it get the best accuracy and latest model.

when i tried to export it and convert it to the required model format using the command: python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o Global.pretrained_model="./output/det_r50_vd/latest" Global.save_inference_dir="./output/det_db_inference/"

it gave the output as :

W0804 12:55:34.817917 4102 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 6.0, Driver API Version: 11.0, Runtime API Version: 10.2 W0804 12:55:34.822103 4102 gpu_resources.cc:91] device: 0, cuDNN Version: 7.6. [2022/08/04 12:55:35] ppocr INFO: load pretrain successful from ./output/det_r50_vd/best_accuracy [2022/08/04 12:55:38] ppocr INFO: inference model is saved to ./output/det_db_inference/inference

and when i loaded the model using the below command:

python3 tools/infer/predict_det.py --det_algorithm="DB" --det_model_dir="./output/det_db_inference/" --image_dir="../image" --use_gpu=True Traceback (most recent call last): File "tools/infer/predict_det.py", line 262, in text_detector = TextDetector(args) File "tools/infer/predict_det.py", line 121, in init args, 'det', logger) File "/home/user/paddle/PaddleOCR/tools/infer/utility.py", line 317, in create_predictor predictor = inference.create_predictor(config) ValueError: (InvalidArgument) The inverse of Fused batch norm variance should be finite. Found nonfinite values! Please check batch_norm_55.w_2 [Hint: Expected std::isfinite(variance_array[i]) == true, but received std::isfinite(variance_array[i]):0 != true:1.] (at /paddle/paddle/fluid/framework/ir/conv_bn_fuse_pass.cc:105)

I am using : NVIDIA 460.27.04
Driver Version: 460.27.04
CUDA Version: 11.2 Python 3.6.10 Distributor ID: Debian Description: Debian GNU/Linux 9.12 (stretch) Model type: detection back end: pretrained_model : ./pretrain_models/ResNet50_vd_ssld_pretrained

PaddlePaddle 2.3.0, compiled with GPU