Tim de Bruin

As an example of the kind of confusion this might prevent: The zoo [example code](https://github.com/larq/zoo/blob/master/docs/examples.md#extract-features-from-an-arbitrary-intermediate-layer-with-bi-real-net) that deals with exactly this point uses get layer by name: ```python outputs=base_model.get_layer("average_pooling2d_8").output ``` The...

I am still very much in favor of this, as I am still running into cases (knowledge distillation) that need this. I had forgotten I was assigned to this. I...

Hi @appleleaves thanks for bringing this to our attention. The code on zoo is complete and should allow training the model. I just tried running it again from zoo and...

The issue is now [fixed](https://github.com/larq/zoo/pull/175) on the master branch. If you pull the latest changes from there, it should now be possible again to train R2B by running the [`TrainR2B`](https://github.com/larq/zoo/blob/c9e96a33380b4b8ea2e96c0c9ad63372b24e6352/larq_zoo/training/multi_stage_experiments.py#L164)...

Hi @appleleaves , > larq installed by pip install larq(should be latest) ~~At the moment the latest fixes are not on PyPy yet. So for now, you can install the...

Just a heads-up though: the training procedure is a simplified version of what we used to train the model on larq-zoo. Our internal code is dependent on our infrastructure and...

> The R2B training has 4 stages, how can I resume it from, for example finishing the first stage? The weights of the intermediate models are saved in a shared...