Amir H. Jadidinejad
Amir H. Jadidinejad
It is great if the program gets the number of stacked layers. I think, [this part](https://github.com/dennybritz/chatbot-retrieval/blob/master/models/dual_encoder.py#L52-L56) of the model should be parameterized.
For a use case, I'm interested to use [triplet/hinge loss](https://en.wikipedia.org/wiki/Triplet_loss), looking at [the implementation of different losses in Thinc](https://github.com/explosion/thinc/blob/master/thinc/loss.py), I can't see something similar. Though there are various implementation in...
It seems that all available datasets contains only explicit feedbacks (user_ids, items_ids, ratings) and the assumption is that the implicit model leverages only (user_ids, item_ids). So, how can I model...
I'm training a standard NMT model using a single GEFORCE GTX 1080 ti (11GB). During training the model, executing nvidia-smi shows that the GPU volatile utilization is always less than...
https://github.com/google/seq2seq/issues/285
Could you reproduce the result of language modeling in the original paper?
For some metrics like nDCG, it is plausible that we have float relevance scores. Is it a way to use pytrec_eval for floating relevance scores? The following sample: ``` import...
providing empty qrel/run file leads to kernel crash! ``` qrel = {} run = {} evaluator = pytrec_eval.RelevanceEvaluator(qrel, pytrec_eval.supported_measures) results = evaluator.evaluate(run) ``` It should be catched in anyway.
`BioCluProcessor` mentioned [here](https://github.com/lum-ai/odinson/tree/master/extra#configuration) as an option for `odinson.extra.processorType`; could you please provide more information about what's the difference between `FastNLPProcessor`, `CluProcessor`, and `BioCluProcessor` please? In addition, choosing `BioCluProcessor` as processorType...
A model has been trained according to the instruction [here](https://github.com/ryankiros/skip-thoughts/tree/master/training). I can load the model using the following commands: ``` import tools embed_map = tools.load_googlenews_vectors() model = tools.load_model(embed_map) ``` After...