Jolideco Uniform Prior=N=1000

Configuration

This is the configuration the deconvolution was run with:

default
MAPDeconvolver
--------------

  n_epochs              : 1000
  beta                  : 1
  learning_rate         : 0.100
  compute_error         : False
  stop_early            : False
  stop_early_n_average  : 10
  display_progress      : True
  device                : cpu
  optimizer             : adam

Model Configuration

This is the configuration the Jolideco model:

default
FluxComponents
--------------

  flux                  :

    use_log_flux        : True
    upsampling_factor   : 1
    frozen              : False
    prior               :

      type              : uniform

Flux

../../../../_images/flux288.png
The plot shows the deconvolved flux image, the reference flux and residuals.

Predicted Counts

../../../../_images/npred288.png
The plot shows the predicted counts correspoding to the deconvolved flux image, the reference flux and residuals.

Metrics

Metric

Value

MSE

23.496

NMI

1.253

NRMSE

0.478

SSI

0.98

MSE = Mean Squared Error, SSI = Structural Similarity Index, NMI = Normalized Mutual Information, NRMSE = Normalized Root Mean Squared Error

Traces

../../../../_images/trace288.png

Files

Results files for download:

point1-bg2-jolideco-uniform-prior=n=1000-chandra-result.fits.gz