File not found error.

[abhishek-kumar-onometra]

I'm getting the following error:

File "/home/mukut/gitlab/corner/data/icdar.py", line 49, in init ic13_samples = open(ic13_list_path, 'r').readlines() IOError: [Errno 2] No such file or directory: '../data/ocr/detection//icdar2013/test_list.txt'

when I executed eval_all.py file.

Any suggestion.

[tayson0825]

I'm getting the following error:

File "/home/mukut/gitlab/corner/data/icdar.py", line 49, in init ic13_samples = open(ic13_list_path, 'r').readlines() IOError: [Errno 2] No such file or directory: '../data/ocr/detection//icdar2013/test_list.txt'

when I executed eval_all.py file.

Any suggestion.

Is your problem solved？

[15926273249]

have you solved this problem?

[tayson0825]

have you solved this problem?

yes .you should make such a .list file (similar to txt file) by yourself , each line is the file name of all test image files

[15926273249]

Can you send me your txt files and the corresponding datasets? Thank you!

[tayson0825]

I did not test it on the icdar2013 task, I did it on COCO-Text, this data set needs to go to the official website to download the train2014 folder (https://rrc.cvc.uab.es/?ch=5&com=downloads )

And then i wrote a python script according to the file name of the test picture in the downloaded data to get the test.list file (Baidu SkyDrive: link: https://pan.baidu.com/s/1lCxm_z8HflyMdGXsKVnUHA Extraction code: cfkp)

[15926273249]

have you tried evaluate_msra.py. First I tested eval_all.py on td500 dataset, then I got the outputs_eval dataset, and I set the root of detection_results_dir as '/outputs_eval/td500/240/res/' in evaluate_msra.py, but I got Traceback (most recent call last): File "evaluate_msra.py", line 153, in recall=float(tp)/(tp+fp) ZeroDivisionError: float division by zero Do you know how to fix it?

[tayson0825]

Yes, I rewritten evaluate_msra.py when I executed COCO-Text. If tp+fp is 0, it may indicate that there is no gt calibration frame. I haven't encountered this problem temporarily

[15926273249]

can you send me your modified evaluate_msra.py ?

[tayson0825]

Ok. But I recommend that you can change it yourself to meet your requirements (Baidu SkyDrive: link: https://pan.baidu.com/s/1cjhctYfjQ-zoz2Jwf0vLdg Extraction code: qnhp)

[15926273249]

have you tried testing on one image instead of the whole dataset ?