Hello all, I want to measure the feature importance in a multivariate time series. The model definition is as follows -
class Network(nn.Module):
def __init__(self, input_size = 4, hidden_dimensions = 16, num_layers = 3, num_outputs = 2, seq_length = 3):
super(Network, self).__init__()
self.num_layers = num_layers
self.hidden_size = hidden_dimensions
self.seq_length = seq_length
self.GRU = nn.GRU(input_size = input_size, hidden_size = hidden_dimensions, num_layers = num_layers,
bias = True, batch_first = True, bidirectional = True)
self.predictor = nn.Linear(in_features = 2 * hidden_dimensions * seq_length, out_features = num_outputs)
def forward(self, input):
batch_size = input.shape[0]
h0 = torch.randn((2 * self.num_layers, batch_size,self.hidden_size))
out, h_n = self.GRU(input, h0)
out = out.reshape(batch_size, 2 * self.hidden_size * self.seq_length)
out = self.predictor(out)
return out
The time series has 3-time steps with 4 feature channels and predicts 2 values that have to regressed.
Therefore, the output of the model is batch, 2
I use Integrated Gradients to find the feature performance as follows -
integratedGradients = IntegratedGradients(model)
attributions_ig, delta = integratedGradients.attribute(aisData, target=Coordinate, return_convergence_delta=True)
I however run into the issue mentioned in the heading.
The full trace is as follows -
Traceback (most recent call last):
File "main.py", line 257, in <module>
attributions_ig, delta = integratedGradients.attribute(aisData, target=Coordinate, return_convergence_delta=True)
File "/home/atharva/.local/lib/python3.8/site-packages/captum/log/__init__.py", line 35, in wrapper
return func(*args, **kwargs)
File "/home/atharva/.local/lib/python3.8/site-packages/captum/attr/_core/integrated_gradients.py", line 286, in attribute
attributions = self._attribute(
File "/home/atharva/.local/lib/python3.8/site-packages/captum/attr/_core/integrated_gradients.py", line 351, in _attribute
grads = self.gradient_func(
File "/home/atharva/.local/lib/python3.8/site-packages/captum/_utils/gradient.py", line 112, in compute_gradients
outputs = _run_forward(forward_fn, inputs, target_ind, additional_forward_args)
File "/home/atharva/.local/lib/python3.8/site-packages/captum/_utils/common.py", line 455, in _run_forward
return _select_targets(output, target)
File "/home/atharva/.local/lib/python3.8/site-packages/captum/_utils/common.py", line 474, in _select_targets
raise AssertionError(
AssertionError: Tensor target dimension torch.Size([50, 2]) is not valid. torch.Size([50, 2])
How can I use Captum for this scenario ?
TIA