Hi

I’m training a Fully Connected NN with Pytorch, and the model seems to perform very well. this is the model, and the hyper-parameters:

**The Model (I’ve not changed the name to FullyConnectedNetworkClassifier)**

As you can see, the output layer has a `sigmoid`

, so my model predicts a probability

**The hyper-parameters**

**The results**

I made a terrible mistake. I didn’t realize that the both dataset’s and unbalanced. The column target has two values, `True`

or `False`

, and, as I said, the unbalancing comes in the form that in both dataset’s the samples with `target=False`

are the 90% (10% of samples with `target=True`

) of the total (both in training and validation)

So my questions:

- My model, as it’s, … is it predicting the probability of the
`True`

class (`target=True`

), or the False one (`target=False`

)? - How can I parametrize
`BCELoss`

with`weights`

? how much should be the magnitud of those`weights`

? What is the in intuition of the`weight`

parameter, exactly? - Could I use
`BCEWithLogitsLoss`

to work with my unbalanced dataset’s?

The Pytorch’docs

https://pytorch.org/docs/stable/generated/torch.nn.BCELoss.html#torch.nn.BCELoss

https://pytorch.org/docs/stable/generated/torch.nn.BCEWithLogitsLoss.html#torch.nn.BCEWithLogitsLoss

Best regards and thanks