Merge pull request #94 from JuliaGNI/add_number_of_network_parameters

Added comment on parameterlength and extended the corresponding function in ANN.
JuliaGNI · Dec 12, 2023 · 858d440 · 858d440
2 parents 19772eb + 99d41e1
commit 858d440
Showing 1 changed file with 10 additions and 0 deletions.
diff --git a/docs/src/tutorials/sympnet_tutorial.md b/docs/src/tutorials/sympnet_tutorial.md
@@ -104,6 +104,16 @@ g_nn = NeuralNetwork(gsympnet, backend, type)
 nothing # hide
 ```
 
+If we want to obtain information on the number of parameters in a neural network, we can do that very simply with the function `parameterlength`. For the `LASympNet`:
+```@example sympnet
+parameterlength(la_nn.model)
+```
+
+And for the `GSympNet`:
+```@example sympnet
+parameterlength(g_nn.model)
+```
+
 *Remark*: We can also specify whether we would like to start with a layer that changes the $q$-component or one that changes the $p$-component. This can be done via the keywords `init_upper` for `GSympNet`, and `init_upper_linear` and `init_upper_act` for `LASympNet`.
 
 We have to define an optimizer which will be use in the training of the SympNet. For more details on optimizer, please see the [corresponding documentation](../Optimizer.md). In this example we use [Adam](../optimizers/adam_optimizer.md):