changing name to Numpy-Neuron

getting rid of unessesary imports

latest update, finishing classification with MNIST! More details on

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

fixed bug that returned same number twice in response

also returning accuracy score from test data from the api

ready for prod

working on readme and adding ml vis submodule

adding accuracy score tracking

adding CORS support

added loss history in the return to the user so they can make graphs and

must specify werkzwug for flask to work on render

forgot to add gunicorn

ignore and removing dockerfile

adding dockerfile

adding accuracy score metric

moving on to testing other datasets!

currently debugging mismatched shape error when computing weights and

init weights and biases, and getting through epochs

init weights and biases

successful example

handling errors well with the neural netork api

working on new python implementation with cleaner code

initial dumb api working

stuck on working with computeOutput function, getting dim error every

mapping activation arg to the actual function

initializing weights and biases

working through Train() function

updated ignore for vim *.swp files when committing from vim terminal

added trainTestSplit() function

adding activation funcs

updated example for new format

significantly decreased the complexity of the API by deciding to make

re configured the Alg interface and the NN sttuct, now we have to work

splitting up code into seperate modules

reads incoming request json if user specifys correctly

initial basic REST API setup

going to use this branch to re make this program in go using the gota

switching back to bas64 encoding/decoding with image byte data

re formatting the api to contain the image bytes in json

stuck

changing the get plot route to return bytes of the image

creating the plot endpoint for getting result images

fixing typos

think I might have to programatically create the path for the images ...

think I was right??

think I have to specify the full path??

more typos

fixing simple typo

instead of returning the image bytes to the api user, we are moving towards hosting them on the backend but we need to be careful moving forwards and make sure that we delete the images after use