Ben Johnson

Results 57 issues of Ben Johnson

Hi -- This is a really great implementation and improvement of MAML! I'm curious about whether it's actually a good idea to let the network meta-learn a nonzero bias initialization...

On [this line](https://github.com/gitabcworld/MatchingNetworks/blob/master/models/AttentionalClassify.py#L28) you're applying a softmax to the similarities. Then [later](https://github.com/gitabcworld/MatchingNetworks/blob/master/models/MatchingNetwork.py#L88) you apply `cross_entropy`, which is a log softmax + NLL loss. I think you probably want to remove...

I see `ROIPooling` layers referenced (eg in `fast-rcnn/models/CaffeNet/test.prototxt`), but I'm having trouble finding where that layer is defined. Anyone have any guidance? Thanks Ben

This is a really wonderful collection of heuristics for CVRPs -- great job! I'm wondering whether there are any algorithms here that are applicable for VRPs with time windows. Alternatively,...

enhancement
question

Hi -- I was wondering where you got the idea for the specific construction of the L-softmax. It seems like maybe you could achieve a similar goal by enforcing a...

Hi -- Do you have an example of using WEASEL to get results close to those reported in [the paper](https://arxiv.org/pdf/1701.07681.pdf)? I'm playing around w/ using WEASEL as a featurizer on...

I see that this data structure supports prefix lookups -- does it also support fuzzy lookups (i.e. all records within Levenshtein distance). If that's not supported in this package /...

question

Hello -- New to numpyro, but really excited to be looking at it! Question: When I call something like ``` nuts = NUTS(model) mcmc = MCMC(nuts, num_warmup=500, num_samples=2000) mcmc.run(rng_key_, data)...

enhancement
help wanted
jax

From the [ConvAI slides](convai.io), it sounds like the Hugging Face submission was based off of this model -- is the code for your ConvAI system available somewhere to take a...

This code is linked from the [fashion-mnist](https://github.com/zalandoresearch/fashion-mnist) repo, w/ very good results. Do you have a script somewhere I might be able to use to reproduce those numbers? Thanks Ben