tofrocwrtdetpepchluna16. Py

[anruoxi123]

Hello, I am now to complete the training and test of the model, the next step to run. / evaluationScript frocwrtdetpepchluna16. py files, before running the file, need to do some what data processing, now I change the path to the project contained in the CSV path, will be submitted to the following error, this file is need to generate its own excuse me? Thanks for comment！

[anruoxi123]

I looked at the val1 and other val folders generated by the test, which do not have.csv files.

[wentaozhu]

Line 144 DeepLung/evaluationScript/frocwrtdetpepchluna16.py uncomment

[anruoxi123]

Hello, according to your suggestion, I have cancelled the annotation of 144 lines, and the program can run part of it, but in the end, the error of CSV file cannot be found, please kindly advise where the problem is.

[wentaozhu]

Oh. I see. The final csv is constructed by concatenating the generated csv from each fold. Now, I think you are using 9 folds and validate 1 fold which is cross-validation. So you need to construct the csv for the validated fold. Do not use all the nodules of the 10 folds to calculate the FROC when you are calculating FROC for the current validated fold.

[anruoxi123]

Ok, thanks for the advice!

Now that my detection part has been trained, I want to run the code of the classification part, namely the classification based on detection. I would like to ask, is the det2cls.py file ok for the detection-based classification?

Is the description of nodule classification in the project aimed at the data of lidc-idri dataset? Is it ok to directly run the main_nodcls.py file if you directly run the node classification? Do you have to run the code to extract the node tag and get the doctor's representation?

Hope comment!

[wentaozhu]

Congratulations!

I think so. If not, you can try main_nodcls.py

Yes, LIDC-IDRI. Yes, first extract nodule in DeepLung/nodcls/data/

Take a look at code and issues in https://github.com/uci-cbcl/DeepLung.git

Maybe there are some updates. Thank you very much for your interest!

[anruoxi123]

Ok, thank you very much!

[tan416tan]

I have same question，I run the tofrocwrtdetpepchluna16. Py can't get csv file ,i want know how to concatenate the generated csv from each fold?

[wentaozhu]

After you get the csv for each fold, you can concatenate them together for the final csv. Please read readme and find an example concatenated csv. 发自网易邮箱大师 On 10/24/2019 21:10, tan416tan wrote: I have same question，I run the tofrocwrtdetpepchluna16. Py can't get csv file ,i want know how to concatenate the generated csv from each fold?

—You are receiving this because you modified the open/close state.Reply to this email directly, view it on GitHub, or unsubscribe. [ { "@context": "http://schema.org", "@type": "EmailMessage", "potentialAction": { "@type": "ViewAction", "target": "https://github.com/wentaozhu/DeepLung/issues/40?email_source=notifications\u0026email_token=ACMYWLNIKGBJ4QWNIW7UKZ3QQGND7A5CNFSM4F3WACZKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECE63RQ#issuecomment-545910214", "url": "https://github.com/wentaozhu/DeepLung/issues/40?email_source=notifications\u0026email_token=ACMYWLNIKGBJ4QWNIW7UKZ3QQGND7A5CNFSM4F3WACZKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECE63RQ#issuecomment-545910214", "name": "View Issue" }, "description": "View this Issue on GitHub", "publisher": { "@type": "Organization", "name": "GitHub", "url": "https://github.com" } } ]