rapidfuzz里面找不到string_metric，导致在pretrain测试的时候中断

[Huangqqqhhh]

[09/02 19:07:09] d2.evaluation.evaluator INFO: Total inference time: 0:08:48.902549 (3.647604 s / img per device, on 2 devices) [09/02 19:07:09] d2.evaluation.evaluator INFO: Total inference pure compute time: 0:01:17 (0.536733 s / img per device, on 2 devices) [09/02 19:07:11] d2.evaluation.text_evaluation INFO: Saving results to ./output/inference/text_results.json [09/02 19:07:18] d2.engine.train_loop ERROR: Exception during training: Traceback (most recent call last): File "/home/hhq/data/code/SwinTextSpotter/detectron2/engine/train_loop.py", line 141, in train self.after_step() File "/home/hhq/data/code/SwinTextSpotter/detectron2/engine/train_loop.py", line 171, in after_step h.after_step() File "/home/hhq/data/code/SwinTextSpotter/detectron2/engine/hooks.py", line 370, in after_step self._do_eval() File "/home/hhq/data/code/SwinTextSpotter/detectron2/engine/hooks.py", line 345, in _do_eval results = self._func() File "/home/hhq/data/code/SwinTextSpotter/detectron2/engine/defaults.py", line 400, in test_and_save_results self._last_eval_results = self.test(self.cfg, self.model) File "/home/hhq/data/code/SwinTextSpotter/detectron2/engine/defaults.py", line 552, in test results_i = inference_on_dataset(model, data_loader, evaluator) File "/home/hhq/data/code/SwinTextSpotter/detectron2/evaluation/evaluator.py", line 180, in inference_on_dataset results = evaluator.evaluate() File "/home/hhq/data/code/SwinTextSpotter/detectron2/evaluation/text_evaluation.py", line 363, in evaluate text_result = self.evaluate_with_official_code(result_path, self._text_eval_gt_path) # None File "/home/hhq/data/code/SwinTextSpotter/detectron2/evaluation/text_evaluation.py", line 332, in evaluate_with_official_code return text_eval_script.text_eval_main(det_file=result_path, gt_file=gt_path, is_word_spotting=self._word_spotting) File "/home/hhq/data/code/SwinTextSpotter/detectron2/evaluation/text_eval_script.py", line 472, in text_eval_main return rrc_evaluation_funcs.main_evaluation(None,det_file, gt_file, default_evaluation_params,validate_data,evaluate_method) File "/home/hhq/data/code/SwinTextSpotter/detectron2/evaluation/rrc_evaluation_funcs.py", line 415, in main_evaluation evalData = evaluate_method_fn(p['g'], p['s'], evalParams) File "/home/hhq/data/code/SwinTextSpotter/detectron2/evaluation/text_eval_script.py", line 381, in evaluate_method edd = string_metric.levenshtein(gtTrans[gtNum].upper(), detTrans[detNum].upper()) NameError: name 'string_metric' is not defined

还有就是请问这是在window系统上实现的嘛

[mxin262]

版本问题，可以试试更低的版本

[wu-yz]

应该是版本太高了，可以卸载rapidfuzz，装一个1.6.0的

[Huangqqqhhh]

可以加个联系方式嘛，一起讨论  

权是海 @.***

 

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2023年10月10日(星期二) 晚上7:43 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [mxin262/SwinTextSpotter] rapidfuzz里面找不到string_metric，导致在pretrain测试的时候中断 (Issue #101)

应该是版本太高了，可以卸载rapidfuzz，装一个1.6.0的

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[Huangqqqhhh]

请问你复现成功了嘛？IC15的测试json注释文件好像用不了

权是海 @.***

 

------------------ 原始邮件 ------------------ 发件人: "mxin262/SwinTextSpotter" @.>; 发送时间: 2023年10月10日(星期二) 晚上7:43 @.>; @.@.>; 主题: Re: [mxin262/SwinTextSpotter] rapidfuzz里面找不到string_metric，导致在pretrain测试的时候中断 (Issue #101)

应该是版本太高了，可以卸载rapidfuzz，装一个1.6.0的

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>