search

awni / ecg

Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network
https://stanfordmlgroup.github.io/projects/ecg2/
GNU General Public License v3.0
679 stars 263 forks source link

Testing #28

Closed QiujieDong closed 3 years ago

QiujieDong commented 5 years ago

Hello, I download data from https://irhythm.github.io/cardiol_test_set/ as the testing data. When I run "python ecg/predict.py .json .hdf5", I get error that "labels.append(d['labels']) Exception KeyError: KeyError". I find that the testing data does not have the 'labels' and 'ecg'. I hope you can tell me how to use it! Thank you!

king-no-crown commented 4 years ago

I have also encountered this problem. How do you solve it?

larissa3m commented 3 years ago

Hello, I download data from https://irhythm.github.io/cardiol_test_set/ as the testing data. When I run "python ecg/predict.py .json .hdf5", I get error that "labels.append(d['labels']) Exception KeyError: KeyError". I find that the testing data does not have the 'labels' and 'ecg'. I hope you can tell me how to use it! Thank you!

Hi, did you make it to solve this issue?

king-no-crown commented 3 years ago

I'm using python3.6.8

------------------ 原始邮件 ------------------ 发件人: "awni/ecg" <notifications@github.com>; 发送时间: 2020年11月10日(星期二) 晚上8:34 收件人: "awni/ecg"<ecg@noreply.github.com>; 抄送: "hjl"<929251610@qq.com>;"Comment"<comment@noreply.github.com>; 主题: Re: [awni/ecg] Testing (#28)

Hello, I download data from https://irhythm.github.io/cardiol_test_set/ as the testing data. When I run "python ecg/predict.py .json .hdf5", I get error that "labels.append(d['labels']) Exception KeyError: KeyError". I find that the testing data does not have the 'labels' and 'ecg'. I hope you can tell me how to use it! Thank you!

Hi, did you make it to solve this issue?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

matru commented 2 years ago

It seems like you cannot run the trained model on custom entries. Like Kardia .json files. Can someone confirm this? There seems to be a exact set of database structure that the trained model can run on.