how to making the LMDB or h5 datasets?

radimspetlik / hr-cnn

HR-CNN - Spetlik, R., Franc, V., Cech, J. and Matas, J. (2018) Visual Heart Rate Estimation with Convolutional Neural Network. In Proceedings of British Machine Vision Conference, 2018

http://cmp.felk.cvut.cz/~spetlrad/ecg-fitness/

GNU General Public License v3.0

53 stars 16 forks source link

how to making the LMDB or h5 datasets? #6

Open amberhappy opened 5 years ago

amberhappy commented 5 years ago

In test-extractor-training.py, you trained the model by one lmdb data, but how to making the LMDB or h5 datasets? And, if i want to train many video data, what should i do?

radimspetlik commented 5 years ago

So, my idea was to give you an example of how the input data should look like. It is true that I did not provide any "data preparing" scripts. Would you like me to create some data-preparation example scripts?

garbatp commented 5 years ago

I think such scripts would be useful. Could you prepare such scripts or help with creation?

Mousumi700 commented 2 years ago

Hello Sir,

Could you please share the script for data preparation?