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)
ValueError: (InvalidArgument) input and filter data type should be consistent, but received input data type is float and filter type is int8_t [Hint: Expected input_data_type == filter_data_type, but received input_data_type:5 != filter_data_type:21.] (at ../paddle/fluid/operators/generator/get_expected_kernel_func.cc:423) [operator < conv2d > error] #13340
Traceback (most recent call last):
File "tools/infer/predict_system.py", line 326, in
main(args)
File "tools/infer/predict_system.py", line 227, in main
dt_boxes, rec_res, time_dict = text_sys(img)
File "tools/infer/predict_system.py", line 109, in call
dt_boxes, elapse = self.text_detector(img)
File "/mnt/workspace/PaddleOCR/tools/infer/predict_det.py", line 394, in call
dt_boxes, elapse = self.predict(img)
File "/mnt/workspace/PaddleOCR/tools/infer/predict_det.py", line 255, in predict
self.predictor.run()
ValueError: (InvalidArgument) input and filter data type should be consistent, but received input data type is float and filter type is int8_t
[Hint: Expected input_data_type == filter_data_type, but received input_data_type:5 != filter_data_type:21.] (at ../paddle/fluid/operators/generator/get_expected_kernel_func.cc:423)
[operator < conv2d > error]
GreatV
commented
1 month ago
问题描述 / Problem Description
PaddleOCR中用导出的模型对测试集进行预测
运行环境 / Runtime Environment
运行命令python3 tools/infer/predict_system.py --det_model_dir=output/CCPD/det_quant/infer --rec_model_dir=output/CCPD/rec_quant/infer --det_limit_side_len=736 --det_limit_type=min --image_dir=/mnt/workspace/PaddleOCR/CCPD2020/ccpd_green/val/ --draw_img_save_dir=infer/quant --use_dilation=true
复现代码 / Reproduction Code
完整报错 / Complete Error Message
Traceback (most recent call last): File "tools/infer/predict_system.py", line 326, in
main(args)
File "tools/infer/predict_system.py", line 227, in main
dt_boxes, rec_res, time_dict = text_sys(img)
File "tools/infer/predict_system.py", line 109, in call
dt_boxes, elapse = self.text_detector(img)
File "/mnt/workspace/PaddleOCR/tools/infer/predict_det.py", line 394, in call
dt_boxes, elapse = self.predict(img)
File "/mnt/workspace/PaddleOCR/tools/infer/predict_det.py", line 255, in predict
self.predictor.run()
ValueError: (InvalidArgument) input and filter data type should be consistent, but received input data type is float and filter type is int8_t
[Hint: Expected input_data_type == filter_data_type, but received input_data_type:5 != filter_data_type:21.] (at ../paddle/fluid/operators/generator/get_expected_kernel_func.cc:423)
[operator < conv2d > error]
可能解决方案 / Possible solutions
附件 / Appendix