Conv_Deconv Model Results

Latest results:

Experiment: Fully convolutional model "conv_deconv""

Input	Model prediction	Correct output	Input + prediction	Input + correct output

Experiment 2 (March 21, 2017)

In experiment 2, we slightly tweaked the model structure, but more importantly, we improved visualization of results.

Input (outer frame)	Model prediction (inner frame)	Correct output (inner frame)	Input + prediction	Input + correct output)

Experiment 1

The first column represents the target inner 32x32 image, wheras the second column represents the corresponding generated prediction of the inner 32x32 image using the outer frame as input.

Target	Prediction