Summary

In experiments 7, randomized validation set is used.(f,f_0 in pixel coordinates)

In experiments 8, only far field patches are used and randomized validation set used. (f,f_0 in pixel coordinates)

In experiments 9, only far field patches are used and randomized validation set used. (f,f_0 in physical coordinates)

Q1 = \[ L1Loss(z**f_0 – x**f_0) \]

Q2 = \[ MSELossLoss(z**f_0 – x**f_0) \]

where f_0 is a gaussian kernel with sigma =1.

experimentssigma of f\(\lambda\)learning
rate
number of
epochs
batch
size
Q1 Q2 Q1 per bubbleQ2 per bubble
exp1/9 10.011e-51501 21.066962 0.805354 0.829031 0.031346
exp2/9 10.005 1e-5 150 1 21.959468 0.812720 0.863606 0.031575
exp3/9 1.50.01 1e-5 150 1 21.031181 0.779206 0.827787 0.030392
exp4/9 1.50.005 1e-5 150 1 20.906547 0.718547 0.823864 0.028081
exp5/9 20.01 1e-5 150 1 22.376564 0.872184 0.881055 0.034107
exp6/9 20.005 1e-5 150 1 23.040157 0.863941 0.907826 0.033746
exp1/8 10.01 1e-5 150 1 12.737782 0.556178 0.501236 0.021680
exp2/8 10.005 1e-5 150 1 13.120187 0.516576 0.517213 0.020148
exp3/81.50.01 1e-5 150 1 13.126150 0.544524 0.517840 0.021331
exp4/81.50.005 1e-5 150 1 13.454322 0.492222 0.531489 0.019310
exp5/820.01 1e-5 150 1 14.191951 0.614085 0.559143 0.024005
exp6/820.005 1e-5 150 1 13.774952 0.536625 0.543580 0.021043
exp1/710.01 1e-5 2001 19.645459 0.981560 0.7747 0.0384
exp2/710.005 1e-5 200 1 20.352445 0.985063 0.802987 0.038526
exp3/71.50.01 1e-5 200 1 18.815349 0.936104 0.742511 0.036656
exp4/71.50.005 1e-5 200 1 19.907855 0.928157 0.785045 0.036292
exp5/7 20.01 1e-5 200 1 19.071611 1.000624 0.753008 0.039267
exp6/720.005 1e-5 200 1 19.766309 0.954419 0.780344 0.037464

Leave a Comment

Your email address will not be published. Required fields are marked *