In the Readout example, a closure is handed into the `analyze` function: https://github.com/BioroboticsLab/IBA/blob/master/notebooks/pytorch_IBA_train_readout.ipynb ``` model_loss_closure = lambda x: -torch.log_softmax(model(x), 1)[:, target].mean() heatmap = iba.analyze(img[None].to(dev), model_loss_closure) ``` This is probably not needed
In the Readout example, a closure is handed into the
analyzefunction:https://github.com/BioroboticsLab/IBA/blob/master/notebooks/pytorch_IBA_train_readout.ipynb
This is probably not needed