-
我应用到crnn去做ocr,就会出现这个问题,调整学习率也没效果
-
部分debug信息
2020-10-11 04:29:24,684-INFO: epoch: 35, iter: 674, lr: 0.000001, 'acc': 0.0, 'loss': 65.148865, time: 0.080
2020-10-11 04:29:24,759-INFO: epoch: 35, iter: 675, lr: 0.000001, 'acc': 0.0, '…
-
Could you give the details of the dataset used?
(Do you used entire IAM dataset??)
-
训练的识别模型crnn+mv3+ctc,数据集是一些车牌的数据集,训练的文字dict也已经配置好,转换inference模型是,config文件是训练时候的config,执行预测时候,训练的best accuracy模型,预测结果全部正确,转换inference模型后,预测结果是英文部分是正确的,但是车牌前面的省份大部分有错误。测试了windows和百度aistudio平台,结果都是有错误。
…
-
PS E:\Python37\PaddleOCR-develop> python .\tools\train.py -c .\configs\rec\rec_icdar15_train.yml
2020-06-16 17:23:35,857-INFO: {'Global': {'algorithm': 'CRNN', 'use_gpu': False, 'epoch_num': 1000, '…
-
First,thank you for the code you provide.
I try to use your code to train for recognizing licence plate.
The char include
alphabet ="""ABCDEFGHJKLMNPQRSTUVWXYZ0123456789-"""
Sometimes the amount …
-
请问轻量化的CRNN是怎么设计的,有代码可以参考吗
-
- I'm trying out OCR projects using CRNN models. This error occurred when the program is executed to model.fit. I tried to use several methods to solve the problem, but nothing seemed to work.
I am …
-
你好, 非常感谢您的项目, 很棒! 我先后跑了检测和识别模型, 当识别模型训练完毕之后, 打算进行单张图片的预测, 因此执行提供的命令, `python3 tools/infer_rec.py -c configs/rec/rec_chinese_lite_train.yml -o Global.checkpoints=./output/rec_CRNN/best_accuracy TestRea…
-
一樣使用
char_dict_cn.json
ord_map_cn.json
可行嗎?
目前使用自己的數據集, 遇上問題
2020-04-14 15:45:32.475062: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at ctc_loss_op.cc:168 : Invalid argu…