[HN Gopher] Vectorflow: Minimalist neural network library faster...
       ___________________________________________________________________
        
       Vectorflow: Minimalist neural network library faster than
       TensorFlow in D
        
       Author : teleforce
       Score  : 66 points
       Date   : 2022-04-15 22:27 UTC (1 days ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | smegsicle wrote:
       | what does it take to get a good word-to-vec--style model going-
       | or are those not 'sparse' ?
        
         | VHRanger wrote:
         | They should be sparse -- the input to Word2Vec is one-hot
         | encodings of words in the models dictionary
        
       | MuffinFlavored wrote:
       | What are interesting things you can do with a minimalist neural
       | network, or even a full blown neural network for that matter?
       | 
       | You just kind of like... train a data set, hope you don't under
       | or overtrain, and then what? Feed it some input, get out an
       | approximate output?
        
         | cinntaile wrote:
         | Their usecase is explained in the accompanying blogpost.
         | https://netflixtechblog.medium.com/introducing-vectorflow-fe...
        
       | hintymad wrote:
       | I wonder if "faster" really matters. The implementation-level
       | optimization seems paled when compared to productivity,
       | ecosystem, and algorithm-level and hardware-level boost. Case in
       | point, Caffe2 wanted to be the backend of PyTorch in FB, yet
       | failed. MxNet claims to be "faster" than PyTorch in pretty much
       | every way and Smola personally pushed orgs in AWS AI really hard
       | to adopt MxNet and Gluon* yet failed. The latter failure is
       | particularly worth mentioning: all teams in AWS AI complied and
       | adopted MxNet but then three years later decided to move to
       | PyTorch. All-in-all, the incremental speed boost was simply
       | irrelevant.
        
         | stainablesteel wrote:
         | if there was constant deployment in some large industrial
         | niche, faster implementations might help you save on your
         | electric bill
        
         | dr_zoidberg wrote:
         | I keep a few projects at work where we train models with
         | Keras+TensorFlow. Twice before I tried to switch to PyTorch,
         | because it did have nicer features/syntax for research and SOTA
         | models, but deploy and support was limited on the toolchain we
         | use, so we had to stay with Keras+TF. I'd still like to switch
         | to PyTorch because of a few goodies, but the deploy of the
         | models on some platforms is still simpler starting from a TF
         | model.
         | 
         | If anyone has a few links or resources to point me to, I'm more
         | than happy to make a third try.
        
       | nivekkevin wrote:
       | I wonder why "faster" matters; Many neural network use cases, at
       | the end, turn into exporting to the model to common formats like
       | ONNX in companion with inference servers like OpenVino, Seldon
       | Core, Triton, TensorRt, etc. I think this is why PyTorch took a
       | big share of the market, because it's in a language that's
       | broadly used by the model designers and it has the ecosystem to
       | also become production-level, which is where the "faster" really
       | matters yet it's beyond what framework one uses while designing
       | the model.
       | 
       | A good use case of this, perhaps is really for the scientists
       | that favor D over Scala and Python?
        
       | softinio wrote:
       | I am curious to know more about what lead to D lang being chosen
       | for this project?
        
         | VHRanger wrote:
         | Check the blog post
         | 
         | - They wanted the same language for implementation and user API
         | 
         | - They wanted a single machine, CPU bound runtime where the
         | executable is the model
         | 
         | Given these, D and Go make sense - easy to pick up, compiles
         | fast and performant.
        
           | softinio wrote:
           | Thanks for heads up on blog had missed that. Great!
        
       | yvdriess wrote:
       | Vectorflow was my gateway drug to Dlang.
        
       ___________________________________________________________________
       (page generated 2022-04-16 23:01 UTC)