-
Basic integration of DragoNN models with DeepChem contrib was just merged in #979. There's a good chunk of work that will have to be done to improve integration. Let's use this issue to coordinate wor…
-
Often, in practice, we wish to compute the contributions w.r.t. the logits of the final sigmoid/softmax, rather than w.r.t. the final network output itself. This is to avoid artifacts that can be caus…
-
Hi all,
Thank you so much for the invitation to captum. Very grateful to all of you for putting this together! I had a quick question regarding the documentation. Currently, in the arguments descri…
-
Hi Avanti,
I have noticed that when we plot the output of sequences, the location of nucleotide starts at index zero (which it needs to be one), and the nucleotide is between two locations(rather…
-
With sequential pytorch layers comprising a ReLU, such as this one
```
self.convLayer1 = nn.Sequential(
nn.Conv1d(256, 512, kernel_size=2, stride=1, padding=0),
nn.…
-
I have tried to use it with RNNs and I get the following error:
`KeyError: 'lstm'` with LSTMs, `KeyError: 'gru'` with GRUs, `KeyError: 'simplernn'` with SimpleRNNs ...
Did anyone else experience t…
-
Paper needs to be read carefully for relevance:
https://dx.doi.org/10.1007/978-3-319-16706-0_20
-
I use deeplift.
If a model's input dimension is (None,None,None,3), when using deeplift, it will raise an exception.
After setting a baseline, it still raise an exception:
"RuntimeError: Baseline…
-
if some dimensions of input are not specified, for example `(None, None, None, 3)`
Method `elrp` works fine, but `deeplift` raises an error. (Both traditional API and Explainer API.)
TypeError: '…
-
Hi, thanks for the module. It's really great :)
I have a problem though. I tried to run it on `InceptionV3` model from keras and I'm getting an error with some methods: `smoothgrad` and `deeplift`…