Open nick-j-braun opened 10 months ago
Hi, if you choose to apply it to a new dataset, you can set it based on the distribution of no. of triplets per time-series in the new dataset. You can set it to 99th percentile for example.
For mimic, the time series length is 880 but it's hard to determine the same for Physionet. I was wondering if you could share the value for physionet as well to keep my experiments consistent.
Under the comment "Find max_len." there is tn explanation or programatic path to follow to know what this value should be. The number 880 is hardcoded in. What should this value be if trying to apply this code to a different project?