I'm getting the following error when trying to run tucker decomposition:
ValueError Traceback (most recent call last)
in <cell line: 3>()
1 print(' Before the decomposition:')
2 print(layer)
----> 3 layer_tucker_decomposed = tucker_decomposition_conv_layer(layer, ranks=[16, 16])
4 print('\n After the decomposition:')
5 print(layer_tucker_decomposed)
in tucker_decomposition_conv_layer(layer, ranks)
5 returns a nn.Sequential object with the Tucker decomposition.
6 """
----> 7 core, [last, first] = partial_tucker(layer.weight.data, modes=[0, 1], rank=ranks, init='svd')
8
9 # A pointwise convolution that reduces the channels from S to R3
ValueError: too many values to unpack (expected 2)
I'm getting the following error when trying to run tucker decomposition:
ValueError Traceback (most recent call last) in <cell line: 3>()
1 print(' Before the decomposition:')
2 print(layer)
----> 3 layer_tucker_decomposed = tucker_decomposition_conv_layer(layer, ranks=[16, 16])
4 print('\n After the decomposition:')
5 print(layer_tucker_decomposed)
ValueError: too many values to unpack (expected 2)