We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
import h5py model_name = "vggnet5" keras_filename = "vggnet5_local_keras_model_CNN_stft_11_frame_173_freq_257_folding_0_best.keras" f = h5py.File(keras_filename)
In auralise.py, I only use param_0, which is weights. Bias values are in param_1
auralise.py
param_0
param_1
>>> f['layer_3']['param_0'] <HDF5 dataset "param_0": shape (64, 64, 3, 3), type "<f4"> >>> f['layer_3']['param_1'] <HDF5 dataset "param_1": shape (64,), type "<f4">
The text was updated successfully, but these errors were encountered:
Hi Keunwoo,
How have you learned these CNN weights? Which dataset and task have you used? '
Thanks, Aseem
Sorry, something went wrong.
I used a private dataset, some details are described in the paper - experiment section.
No branches or pull requests
In
auralise.py
, I only useparam_0
, which is weights. Bias values are inparam_1
The text was updated successfully, but these errors were encountered: