Commits · Jensen-holm/Numpy-Neuron

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

4dc8296

Jensen-holm commited on Apr 19

stuck on getting this package to work on pypi

f7ea12e

Jensen-holm commited on Apr 19

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

e53a40c

Jensen-holm commited on Apr 19

better about and readme docs

7855334

Jensen-holm commited on Apr 19

Merge pull request #1 from Jensen-holm/package

84ec87c
unverified

Jensen-holm commited on Apr 19

making it a python package on PyPI

75481dd

Jensen-holm commited on Apr 19

Moving towards making this a python package for simple neural network

03f2b37

Jensen-holm commited on Apr 19

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

9117cbd

Jensen-holm commited on Apr 17

fixing bug that happened with a type that I made, I think huggingface

de85694

Jensen-holm commited on Apr 17

features added:

e11b37a

Jensen-holm commited on Apr 17

adding Sigmoid as an option for output layer activation

28a7ac6

Jensen-holm commited on Apr 16

changing name to Numpy-Neuron

b471057

Jensen-holm commited on Apr 15

getting rid of unessesary imports

e236c9a

Jensen-holm commited on Apr 15

latest update, finishing classification with MNIST! More details on

6d0453c

Jensen-holm commited on Apr 15

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

6307b4f

Jensen-holm commited on Apr 12

fixed bug that returned same number twice in response

d04aaf5

Jensen-holm commited on Oct 16, 2023

also returning accuracy score from test data from the api

bff0f22

Jensen-holm commited on Oct 15, 2023

ready for prod

336625e

Jensen-holm commited on Oct 13, 2023

working on readme and adding ml vis submodule

3ca18fe

Jensen-holm commited on Oct 13, 2023

adding accuracy score tracking

303df47

Jensen-holm commited on Oct 12, 2023

adding CORS support

8ea5c07

Jensen-holm commited on Oct 11, 2023

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

2fc4a94

Jensen-holm commited on Oct 11, 2023

must specify werkzwug for flask to work on render

ceca02c

Jensen-holm commited on Oct 11, 2023

forgot to add gunicorn

843007e

Jensen-holm commited on Oct 11, 2023

ignore and removing dockerfile

abcc2e0

Jensen-holm commited on Oct 11, 2023

adding dockerfile

a4c4ba0

Jensen-holm commited on Oct 11, 2023

adding accuracy score metric

03176c2

Jensen-holm commited on Oct 11, 2023

moving on to testing other datasets!

9e506b7

Jensen-holm commited on Oct 11, 2023

currently debugging mismatched shape error when computing weights and

880505a

Jensen-holm commited on Oct 11, 2023

init weights and biases, and getting through epochs

84bbd7d

Jensen-holm commited on Oct 11, 2023

init weights and biases

38e3b7b

Jensen-holm commited on Oct 11, 2023

successful example

14841f9

Jensen-holm commited on Oct 11, 2023

handling errors well with the neural netork api

8c348c5

Jensen-holm commited on Oct 11, 2023

working on new python implementation with cleaner code

29cce3f

Jensen-holm commited on Oct 11, 2023

initial dumb api working

2c781f8

Jensen-holm commited on Oct 11, 2023

stuck on working with computeOutput function, getting dim error every

0987346

Jensen-holm commited on Oct 11, 2023

mapping activation arg to the actual function

0a04cd7

Jensen-holm commited on Oct 11, 2023

initializing weights and biases

59ae052

Jensen-holm commited on Oct 11, 2023

working through Train() function

6b47160

Jensen-holm commited on Oct 10, 2023

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

c4864dc

Jensen-holm commited on Oct 10, 2023

added trainTestSplit() function

554811e

Jensen-holm commited on Oct 10, 2023

adding activation funcs

27c0b63

Jensen-holm commited on Oct 10, 2023

updated example for new format

fae8f77

Jensen-holm commited on Oct 10, 2023

significantly decreased the complexity of the API by deciding to make

eec3b88

Jensen-holm commited on Oct 9, 2023

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

a4aa491

Jensen-holm commited on Oct 9, 2023

splitting up code into seperate modules

dfd3544

Jensen-holm commited on Oct 9, 2023

reads incoming request json if user specifys correctly

b5b4a38

Jensen-holm commited on Oct 9, 2023

initial basic REST API setup

5d966be

Jensen-holm commited on Oct 9, 2023

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

da3cde4

Jensen-holm commited on Oct 9, 2023

switching back to bas64 encoding/decoding with image byte data

f308820

Jensen-holm commited on Oct 7, 2023

Commit History

fixed bug where I forgot to change the name from nn to numpyneuron 4dc8296

stuck on getting this package to work on pypi f7ea12e

python package not really working, but it is all set up okay I think e53a40c

better about and readme docs 7855334

Merge pull request #1 from Jensen-holm/package 84ec87c unverified

making it a python package on PyPI 75481dd

Moving towards making this a python package for simple neural network 03f2b37

getting rid of regression tab, thinking about having a custom data tab 9117cbd

fixing bug that happened with a type that I made, I think huggingface de85694

features added: e11b37a

adding Sigmoid as an option for output layer activation 28a7ac6

changing name to Numpy-Neuron b471057

getting rid of unessesary imports e236c9a

latest update, finishing classification with MNIST! More details on 6d0453c

switching to gradio and a complete rewrite that I did over in the 6307b4f

fixed bug that returned same number twice in response d04aaf5

also returning accuracy score from test data from the api bff0f22

ready for prod 336625e

working on readme and adding ml vis submodule 3ca18fe

adding accuracy score tracking 303df47

adding CORS support 8ea5c07

added loss history in the return to the user so they can make graphs and 2fc4a94

must specify werkzwug for flask to work on render ceca02c

forgot to add gunicorn 843007e

ignore and removing dockerfile abcc2e0

adding dockerfile a4c4ba0

adding accuracy score metric 03176c2

moving on to testing other datasets! 9e506b7

currently debugging mismatched shape error when computing weights and 880505a

init weights and biases, and getting through epochs 84bbd7d

init weights and biases 38e3b7b

successful example 14841f9

handling errors well with the neural netork api 8c348c5

working on new python implementation with cleaner code 29cce3f

initial dumb api working 2c781f8

stuck on working with computeOutput function, getting dim error every 0987346

mapping activation arg to the actual function 0a04cd7

initializing weights and biases 59ae052

working through Train() function 6b47160

updated ignore for vim *.swp files when committing from vim terminal c4864dc

added trainTestSplit() function 554811e

adding activation funcs 27c0b63

updated example for new format fae8f77

significantly decreased the complexity of the API by deciding to make eec3b88

re configured the Alg interface and the NN sttuct, now we have to work a4aa491

splitting up code into seperate modules dfd3544

reads incoming request json if user specifys correctly b5b4a38

initial basic REST API setup 5d966be

going to use this branch to re make this program in go using the gota da3cde4

switching back to bas64 encoding/decoding with image byte data f308820

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

4dc8296

stuck on getting this package to work on pypi

f7ea12e

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

e53a40c

better about and readme docs

7855334

Merge pull request #1 from Jensen-holm/package

84ec87c
unverified

making it a python package on PyPI

75481dd

Moving towards making this a python package for simple neural network

03f2b37

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

9117cbd

fixing bug that happened with a type that I made, I think huggingface

de85694

features added:

e11b37a

adding Sigmoid as an option for output layer activation

28a7ac6

changing name to Numpy-Neuron

b471057

getting rid of unessesary imports

e236c9a

latest update, finishing classification with MNIST! More details on

6d0453c

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

6307b4f

fixed bug that returned same number twice in response

d04aaf5

also returning accuracy score from test data from the api

bff0f22

ready for prod

336625e

working on readme and adding ml vis submodule

3ca18fe

adding accuracy score tracking

303df47

adding CORS support

8ea5c07

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

2fc4a94

must specify werkzwug for flask to work on render

ceca02c

forgot to add gunicorn

843007e

ignore and removing dockerfile

abcc2e0

adding dockerfile

a4c4ba0

adding accuracy score metric

03176c2

moving on to testing other datasets!

9e506b7

currently debugging mismatched shape error when computing weights and

880505a

init weights and biases, and getting through epochs

84bbd7d

init weights and biases

38e3b7b

successful example

14841f9

handling errors well with the neural netork api

8c348c5

working on new python implementation with cleaner code

29cce3f

initial dumb api working

2c781f8

stuck on working with computeOutput function, getting dim error every

0987346

mapping activation arg to the actual function

0a04cd7

initializing weights and biases

59ae052

working through Train() function

6b47160

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

c4864dc

added trainTestSplit() function

554811e

adding activation funcs

27c0b63

updated example for new format

fae8f77

significantly decreased the complexity of the API by deciding to make

eec3b88

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

a4aa491

splitting up code into seperate modules

dfd3544

reads incoming request json if user specifys correctly

b5b4a38

initial basic REST API setup

5d966be

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

da3cde4

switching back to bas64 encoding/decoding with image byte data

f308820