1.4 GB

1 contributor

This is an implementation of the Google's Vision Transformer large patch 32 that is used for music classification into different genres. The dataset used is the gtzan dataset which has melspectrograms of many songs.

faba7b5 verified over 1 year ago

.gitattributes
1.56 kB

Upload 12 files over 1 year ago
README.md
167 Bytes

This is an implementation of the Google's Vision Transformer large patch 32 that is used for music classification into different genres. The dataset used is the gtzan dataset which has melspectrograms of many songs. over 1 year ago
all_results.json
391 Bytes

Upload 12 files over 1 year ago
config.json
1.1 kB

Upload 12 files over 1 year ago
eval_results.json
203 Bytes

Upload 12 files over 1 year ago
model.safetensors
350 MB
xet

Upload 12 files over 1 year ago
optimizer.pt
700 MB
xet

Upload 12 files over 1 year ago
preprocessor_config.json
578 Bytes

Upload 12 files over 1 year ago
rng_state.pth
14.2 kB
xet

Upload 12 files over 1 year ago
scheduler.pt
1.06 kB
xet

Upload 12 files over 1 year ago
state.db
350 MB
xet

Upload 12 files over 1 year ago
train_results.json
209 Bytes

Upload 12 files over 1 year ago
trainer_state.json
44.4 kB

Upload 12 files over 1 year ago
training_args.bin
4.92 kB
xet

Upload 12 files over 1 year ago