wellton/Emosic

Fork 0

T

Charlie Hewitt 8a1cd872c9 update evaluate

2018-01-03 16:49:29 +00:00

app/aff-song

add probs to us and update evaluate

2018-01-03 13:47:57 +00:00

M_ALEX

remove old stuff

2017-12-28 11:03:40 +00:00

M_MOB

remove old stuff

2017-12-28 11:03:40 +00:00

M_VGG

remove old stuff

2017-12-28 11:03:40 +00:00

.gitignore

update nets

2017-12-27 12:48:50 +00:00

convert.py

final models

2017-12-28 11:01:45 +00:00

data_p

updated net

2017-12-19 18:19:00 +00:00

evaluate.py

update evaluate

2018-01-03 16:49:29 +00:00

icon.png

Add app

2017-12-10 16:34:39 +00:00

icon.psd

Add app

2017-12-10 16:34:39 +00:00

kalpha.py

update nets

2017-12-27 12:48:50 +00:00

LICENSE

Update LICENSE

2017-12-27 17:16:59 +00:00

MobAffNetC.mlmodel

final models

2017-12-28 11:01:45 +00:00

MobAffNetR.mlmodel

final models

2017-12-28 11:01:45 +00:00

net.py

final models

2017-12-28 11:01:45 +00:00

parse.py

update nets

2017-12-27 12:48:50 +00:00

README.md

change name

2017-12-27 12:49:42 +00:00

training_labels.npy

update net + add dataset files

2017-12-14 10:12:18 +00:00

training_paths.npy

update net + add dataset files

2017-12-14 10:12:18 +00:00

validation_labels.npy

update net + add dataset files

2017-12-14 10:12:18 +00:00

validation_paths.npy

update net + add dataset files

2017-12-14 10:12:18 +00:00

README.md

Emosic

Song recommendations based on user affect using CNNs for emotion classification and valence/arousal regression. Predictions made using the Spotify Web API.

CNNs trained on AffectNet using Keras and deployed to iOS by conversion to coreML using coremltools.