wxdang / MSCRED

tensorflow implement the paper A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
60 stars 28 forks source link

gap time between each segment #6

Open kaixuan0623 opened 3 years ago

kaixuan0623 commented 3 years ago

gap time between each segment is set to 10, i.e. the (start) timestamps between two adjacent signature matrices should be 10, but when you generate each of the signature matrix, the gap time is 1

in generation_signature_matrice.py:

    for t in range(win, self.signature_matrices_number):
        raw_data_t = raw_data[:, t - win:t]
        signature_matrices[t] = np.dot(raw_data_t, raw_data_t.T) / win

    return signature_matrices

i think when computing raw_data_t, we should consider that

e.g.

for t in range(signature_matrices_number):
    raw_data_t = raw_data[:, t*gap_time:(t*gap_time + window_size)]
    signature_matrices[t] = np.dot(raw_data_t, raw_data_t.T) / window_size 
return signature_matrices
cmmxby commented 2 years ago

I quite agree with you.I quite agree with you. Have you finished debugging? Could you share your code? Could you share it with me. My email is cmmxby@163.com