search

bakqui / ST-MEM

[ICLR2024] Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram
Other
32 stars 5 forks source link

Questions about pre-training #2

Closed rkfkfkfkr closed 2 months ago

rkfkfkfkr commented 8 months ago

Hello, I'd like to conduct pre-training on the st-mem model using the same dataset. I have all the datasets ready. My question pertains to the contents of st_mem/configs/pretraining.yaml. Could you please explain the components of the dataset section in pretraining.yaml? Specifically, could you describe how to generate ningbo_shaoxing_code15_10s.pkl? issue 질문

dduddus commented 8 months ago

Hello, thank you for your interset in our works. The codes we uploaded in supplementary files focus on finetuning using the PTB-XL dataset. The whole training process(including data pre-processing) would be uploaded this repository soon.

VaeReol commented 8 months ago

hey, where do you get the code you provided above?

LewisJeny commented 7 months ago

hey, where do you get the code you provided above?

dduddus commented 4 months ago

Please refer to ./data/README.md and ./data/process_ecg.py for details. Then you can create your own dataset.