Commit History

  1. Update requirements.txt

    Verified signature
    599dfe7

  1. changing the example to what is actually in the example

    9c1370a

  1. Merge pull request #2 from Jensen-holm/dev⁠

    Unverified signature
    d6cc61a
  2. making the example code cleaner

    Jensen Holm
    498c4e0
  3. loss functions now just have staticmethods

    Jensen Holm
    d7ea050
  4. adding unit tests for activation functions (using pytest)

    Jensen Holm
    ff1254a

  1. adding example documentation

    Jensen Holm
    9249567
  2. format

    Jensen Holm
    05819f2
  3. adding example program 'example.py'

    Jensen Holm
    284dbf2

  1. found the bug in setup.py that was stopping me from getting the package⁠

    adc3f91

  1. readme updates

    2cac6be
  2. pypi package works!

    a094ad4
  3. fixed bug where I forgot to change the name from nn to numpyneuron

    4dc8296
  4. stuck on getting this package to work on pypi

    f7ea12e
  5. python package not really working, but it is all set up okay I think

    e53a40c
  6. better about and readme docs

    7855334
  7. Merge pull request #1 from Jensen-holm/package⁠

    Unverified signature
    84ec87c
  8. making it a python package on PyPI

    75481dd
  9. Moving towards making this a python package for simple neural network⁠

    03f2b37

  1. getting rid of regression tab, thinking about having a custom data tab⁠

    9117cbd
  2. fixing bug that happened with a type that I made, I think huggingface⁠

    de85694
  3. features added:⁠

    e11b37a

  1. adding Sigmoid as an option for output layer activation

    28a7ac6

  1. changing name to Numpy-Neuron

    b471057
  2. getting rid of unessesary imports

    e236c9a
  3. latest update, finishing classification with MNIST! More details on⁠

    6d0453c

  1. switching to gradio and a complete rewrite that I did over in the⁠

    6307b4f

  1. fixed bug that returned same number twice in response

    d04aaf5

  1. also returning accuracy score from test data from the api

    bff0f22

  1. ready for prod

    336625e
  2. working on readme and adding ml vis submodule

    3ca18fe

  1. adding accuracy score tracking

    303df47

  1. adding CORS support

    8ea5c07
  2. added loss history in the return to the user so they can make graphs and⁠

    2fc4a94
  3. must specify werkzwug for flask to work on render

    ceca02c
  4. forgot to add gunicorn

    843007e
  5. ignore and removing dockerfile

    abcc2e0
  6. adding dockerfile

    a4c4ba0
  7. adding accuracy score metric

    03176c2
  8. moving on to testing other datasets!

    9e506b7
  9. currently debugging mismatched shape error when computing weights and⁠

    880505a
  10. init weights and biases, and getting through epochs

    84bbd7d
  11. init weights and biases

    38e3b7b
  12. successful example

    14841f9
  13. handling errors well with the neural netork api

    8c348c5
  14. working on new python implementation with cleaner code

    29cce3f
  15. initial dumb api working

    2c781f8
  16. stuck on working with computeOutput function, getting dim error every⁠

    0987346
  17. mapping activation arg to the actual function

    0a04cd7
  18. initializing weights and biases

    59ae052