You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Yep, #71 is a milestone here. When I take a look at some TF models (mobilenets) I see Input and output dimensions correctly specified in the right panel - is it the case in which the model well specifies the tensor shapes?
Many papers show visually how an image input gets progressively shrunk but deepened by strided convolutions or expanded by deconvolutions.
Would be nice to have an isometric representation of the WHC input and output, in case of 3-dimensional geometries (batch=1).
The 2 isometric parallelepipeds could be drawn in the Node/Net panel.
The text was updated successfully, but these errors were encountered: