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
Hi,
I would like to just sample random genotypes using your code without learning alphas_normal, alphas_reduce.
I'm using the following code and it seems to work fine. Just wanted to check in if you can notice any caveats with using it or suggest a simpler approach.
set_random_seed(111) # some function to set seed everywhere
steps = np.random.randint(1,5)
model = cnn.model_search.Network(n_ch, n_classes, n_layers, criterion,
steps=steps, multiplier=steps) # multiplier seems to be required to be equal steps
genotype = model.genotype() # random genotype
The text was updated successfully, but these errors were encountered:
Hi,
I would like to just sample random genotypes using your code without learning alphas_normal, alphas_reduce.
I'm using the following code and it seems to work fine. Just wanted to check in if you can notice any caveats with using it or suggest a simpler approach.
The text was updated successfully, but these errors were encountered: