Neta Zmora

This ```input``` tensor is used to sample the dictionary - to randomly choose the first word in the input sequence. The next time ```input``` is used, it is already after...

@luuuyi yes, I agree with you. This occurred to me some time after I posted the question, but I didn't think to update here. Thanks for answer!

Hi @gitti123, > I think it is because of the expectation that the batchnormalization layer will come after the convolutional layer and not the other way round here Exactly :-)...

Looks good - thanks! Can you add a test that fails without the fix and succeeds with the new code (to [here](https://github.com/NervanaSystems/distiller/blob/master/tests/test_pruning.py))? I'd like to have a regression test so...

Hi @trougnouf, Please let me know if you plan to pursue this PR. Thanks! Neta

Hi @bezorro , You are correct - this is a bug and should be fixed as you suggested. If you want to send us a fix PR, that would be...

> This happens only when trying to resume training on GPU, when the checkpoint was previously saved for CPU. Yes, we support training on the GPU and then loading on...

> @nzmora note that as far as I can tell, the hooks implemented by all collectors (inc. your original ones) assume the inputs are `torch.Tensor`s. So while @barrh ran the...

Hi, Quantization-Aware Training (QAT) in Distiller is described in several places: - [Overview](https://nervanasystems.github.io/distiller/quantization.html#quantization-aware-training) - [YAML syntax details](https://nervanasystems.github.io/distiller/schedule.html#quantization-aware-training) - [Preparing a model for quantization](https://nervanasystems.github.io/distiller/prepare_model_quant.html) - [Algorithm](https://nervanasystems.github.io/distiller/algo_quantization.html#quantization-aware-training) - [Design](https://nervanasystems.github.io/distiller/design.html#quantization-aware-training) - [Example QAT...

Hi @longzeyilang , Please add more information: which Distiller API are you trying to use? Cheers, Neta