... | @@ -11,6 +11,8 @@ |
... | @@ -11,6 +11,8 @@ |
|
|
|
|
|
## Weight plotter
|
|
## Weight plotter
|
|
The weight plotter can visualize the filter trained in the neural network (currently limited to convolutional layer).
|
|
The weight plotter can visualize the filter trained in the neural network (currently limited to convolutional layer).
|
|
|
|
After splitting the convolutional layer into its filters, the matrices for every filter are rendered as a block of grayscale pixels.
|
|
|
|
Very light pixels represent the weights with the higher parameter values, darker pixels the weights with the lower parameter values.
|
|
![image](/uploads/ea6a7099e4e1c3f2ee052233215fc810/image.png)
|
|
![image](/uploads/ea6a7099e4e1c3f2ee052233215fc810/image.png)
|
|
By use of the three comboboxes the desired session, snapshot and layer can be chosen respectively.
|
|
By use of the three comboboxes the desired session, snapshot and layer can be chosen respectively.
|
|
By holding and dragging the left mouse button, the visualization can be panned in a desired direction.
|
|
By holding and dragging the left mouse button, the visualization can be panned in a desired direction.
|
... | | ... | |