phuselab / pyVHR

Python framework for Virtual Heart Rate

Home Page:http://phuselab.di.unimi.it/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question about code + output

Laura-0201 opened this issue · comments

Hello,

I'm including pyVHR in my thesis, however I'm really stuck and was hoping someone could help me :). For the purpose of my thesis I only have to use the timepoints and BPM. I got a lot of errors on the original code, so my supervisor gave me adjusted code. I do get an output now, but do not know how to interpet them. So my question is, does this code even work properly this way? If so how do I interpet the output?

Code:
`
import pyVHR as vhr
import numpy as np
from pyVHR.analysis.pipeline import Pipeline
from pyVHR.plot.visualize import *
import os
import plotly.express as px
from pyVHR.utils.errors import getErrors, printErrors, displayErrors

from pyVHR.analysis.pipeline import Pipeline
from pyVHR.plot.visualize import *
from pyVHR.utils.errors import getErrors, printErrors, displayErrors

from pyVHR.extraction.utils import sig_windowing

fps = vhr.extraction.get_fps("C:\Users\laura\Documents\Semester 6\Thesis\VS8.MOV")
#wsize = 8 # seconds of video processed (with overlapping) for each estimate
#test_bvp = sigGT.data
#bpmGT, timesGT = sigGT.getBPM(wsize)

pipe = Pipeline() # object to execute the pipeline
bvps, timesES, bpmES = pipe.run_on_video("C:\Users\laura\Documents\Semester 6\Thesis\VS8.MOV",
roi_method='convexhull',
roi_approach='patches',
method='cpu_POS',
bpm_type='welch',
pre_filt=False,
post_filt=True,
verb=True,
cuda=False)

print('time:', timesES, 'bpm:', bpmES, 'bvps:', bvps)`

Output:
image

I think the best way to test is using the video in a open dataset like UBFC. The output is closely depend on your input video.