Table 2.
Deep-Channel predicted labels | |||||||
---|---|---|---|---|---|---|---|
0 | 1 | 2 | 3 | 4 | 5 | ||
True labels | 0 | 96890 | 726 | 0 | 0 | 0 | 0 |
1 | 9 | 2371 | 0 | 0 | 0 | 0 | |
2 | 0 | 0 | 0 | 0 | 0 | 0 | |
3 | 0 | 0 | 0 | 0 | 0 | 0 | |
4 | 0 | 0 | 0 | 0 | 0 | 0 | |
5 | 0 | 0 | 0 | 0 | 0 | 0 |
Label 0 = no channels open, label 1 = one channel open. Note that Deep-Channel is trained to recognise up to 5 channels opening at a time, however, with only one channel active at a time, the maximum ground truth class (True Label) is label 1 (one channel open). The emboldened numbers are the number of data points correctly predicted by Deep-Channel