Show HN: TensorSpace.js – Neural network 3D visualization framework

Re:Show HN: TensorSpace.js – Neural network 3D visualization... by p1esk on Tuesday November 13, 2018 @04:08PM (#18444919)

To provide some feedback:

1. display weights and gradients (in addition to activations)

2. display how activations/weights/gradients change during training. For example, I should be able to point to checkpoint directory where my model is saved every epoch (or every few iterations), and then hit 'play' button to see how a particular feature map or weights filter is changing as I move between epochs/iterations.

3. display which inputs contribute the most to the activations, at every layer.

These additional features would be very useful for debugging, for model compression, for identifying information flows (e.g. in a DenseNet), for saliency analysis, and probably for other things as well.

[ Parent | on HN ]

Re:Show HN: TensorSpace.js – Neural network 3D visualization... by syt123450 on Thursday November 15, 2018 @01:56PM (#18462109)

Thanks for your feedback, I am planing to visualize weights in next version of TensorSpace. These days, I add a "live loader" for TensorSpace, user can use this API to visualize online training process.

And for others features, we are discussing how to integrate them with TensorSpace, looking forward to your further suggestions.

[ Parent | on HN ]