Ben Johnson

Data for tensorflow benchmark

1

Does anyone have a link to the dataset that's used in the tensorflow benchmark? The run command is: ``` autoencoder.py -u 1024 -b 256 -i 1082 -v54 --vocab_size 27278 -l...

Output layer question

6

The output layer in these networks is often a bottleneck, because you have to do a `(batch_size, hidden_dim)` by `(hidden_dim, num_classes)` dense matrix multiplication. It doesn't seem like you'd get...

Output format

1

I ran the code, and just want to be clear that I'm understanding the output format. ``` $ python train.py --which-dataset C10 $ python evaluate.py --SMASH=SMASH_D12_K4_N8_Nmax64_maxbneck2_SMASH_C10_seed0_100epochs --which-dataset C10 $ python...

LFW benchmarking

3

Hi -- Have you ever used this package to reproduce the LFW benchmark numbers as reported in the original paper? Thanks Ben

implement unsupervised version

1

Need to implement: - [ ] method to generate context pairs - [ ] edge sampler - [ ] triplet loss model

I noticed that you run the attention through a sigmoid because you were having numerical problems: https://github.com/codekansas/keras-language-modeling/blob/master/attention_lstm.py#L54 This may work, but I think that should actually be a softmax. In...

Tensorflow and sonnet versions?

1

I'm trying to run w/ the following versions in python==3.6.5 ``` >>> sonnet.__version__ '1.27' >>> tensorflow.__version__ '1.12.0' ``` and getting the following error: ``` $ python train.py --problem=mnist --save_path=./mnist WARNING:tensorflow:From...

L1-regularized PPR on directed graphs?

2

Hello -- I'm interested in trying to apply the L1-regularized PPR on a directed graph ... do you know if there's an implementation of that somewhere? Or - if not...

Parallel version

1

Any plans to release a multi-GPU version of this? It looks like we should be able to run the `meta_batch_size` iterations of the outer loop in `reptile.train_step` in parallel on...

datasets

3

Are the datasets references in the README available for download somewhere?