Get confidence of prediciton per regressed coordinate about dsntnn HOT 8 CLOSED

I think I could use _divergence_reg_losses with different sigma_t values and mu_t as the regressed coordinate and then see which sigma_t has the lowest loss. That would be kind of a brute force approach, but better than nothing

from dsntnn.

If you look at the variance_reg_losses function you can find an example of calculating the variance of heatmaps:

I haven't tried using it this way myself, but it could be possible to use this sort of calculation as a proxy for confidence.

from dsntnn.

Very nice, have not seen this function. This seems to work pretty good in my first tests. Just have to find a nice way to transform it into values between 0 and 1, but I'll figure it out. Thank you!

from dsntnn.

@anibali, I use the function variance_reg_losses() with to get confidence. But the confidence is 0.05 very low with unnormalized_heatmaps and 3.9954e+08 very high with normalized_heatmaps. How to get normal landmark confidence? if I make traditional gauss heatmap like figure2b in the paper, the heatmap value is [0, 1], and I will try it.

from dsntnn.

You will need to calibrate the outputs from variance_reg_losses yourself. Keep in mind that it should have an inverse relationship with confidence (a large value indicates low confidence). It should be used with normalised heatmaps.

Note that this is not something that I have tried myself, so you will need to do some experimenting.

from dsntnn.

@anibali Thanks your replay. I have cablibrated the outputs and experimented. In the example of basic_usage.md, add three different points [24, 27] [28, 32] [32, 15]. But the three points output values have big difference, eg, 0.2, 0.02, 0.12. Is it normal? Cablibrate by abs(output - output_mean)/(max_output - min_output) and is it right? If only one point as input, this cablibrate method doesnot work.

If it can make gauss like function gaussian(img, pt, sigma) ? And I have a try.

from dsntnn.

You just have to experiment with your actual data. There is no way to tell whether the spread of numbers is meaningful for three points, you have to observe what the values are like for both good and bad predictions to see whether they are correlated.

from dsntnn.

ok, thanks, I have a try.

from dsntnn.