jakobkrzyston / complex_convolutions Goto Github PK

hello, I'm interested in your work and try to run your code, but I found that the constant matrix in your code does not match that in your paper, which is [[0 1 0] [-1 0 1]] in your code and it's transposed form is [[0 -1] [1 0] [0 1]]. That transpose form differs from the matrix your paper proposed, which is [[1 0] [0 1] [-1 0]]. So I wonder why you proposed [[0 1 0] [-1 0 1]] as constant matrix in lambda expression instead of [[1 0 -1] [0 1 0]]. Thanks a lot. By the way, it's really a fascinating idea.

Traceback (most recent call last):
File "C:\Users###\Desktop\Complex_Convolutions-master\Complex_Convolutions-master\Complex_Convolutions\run.py", line 112, in
train_models.train(model, model_name, X_train1, X_test1, Y_train1, Y_test1, tag, load_weights, epochs=100, batch_size = 1024)
File "C:\Users###\Desktop\Complex_Convolutions-master\Complex_Convolutions-master\Complex_Convolutions\train_models.py", line 37, in train
history = model.fit(X_train1,
File "C:\Users###\anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users####\anaconda3\lib\site-packages\keras\engine\data_adapter.py", line 1418, in _make_class_weight_map_fn
class_ids = list(sorted(class_weight.keys()))
AttributeError: 'str' object has no attribute 'keys'

Missing 'activation_maximizations' module