yashkant / Elastic-Weight-Consolidation

This is an implementation of Elastic Weight Consolidation algorithm introduced in Overcoming catastrophic forgetting in neural networks.

Home Page:https://arxiv.org/pdf/1612.00796.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Version conflicts

rschlund opened this issue · comments

Which versions of tensorflow, numpy etc. do i have to use to get your code running? When trying to run it with actual versions i get:


TypeError Traceback (most recent call last)
in
----> 1 train_model(model, mnist, [mnist], 800, 20) #train model on task-A

in train_model(model, train_set, test_sets, num_iters, disp_freq, lams)
20 test_accs = []
21 for i in range(len(test_sets)):
---> 22 test_accs.append(np.zeros(num_iters / disp_freq))
23
24 for it in range(num_iters):

TypeError: 'float' object cannot be interpreted as an integer