Evalds Urtans

Results 8 comments of Evalds Urtans

This would be excellent feature like in EAZ Obfuscator: ![image](https://user-images.githubusercontent.com/1777062/42680202-f370fa30-868c-11e8-8e23-a04cf0829fce.png)

If you could make changes and submit pull request, I would gladly merge into master

For example ConNet-RNN looks like this: ``` model_target.add(TimeDistributed(Conv2D(32, (8, 8), strides=(4, 4), kernel_initializer=glorot_uniform(seed=init_seed), padding='same', activation='relu', input_shape=(high_dimensions_width, high_dimensions_height, high_dimensions_channels)), input_shape=(params['frames_back'], high_dimensions_width, high_dimensions_height, high_dimensions_channels))) model_target.add(TimeDistributed(Conv2D(64, (4, 4), strides=(2, 2), kernel_initializer=glorot_uniform(seed=init_seed), activation='relu'))) model_target.add(TimeDistributed(Conv2D(64,...

Thank you for answering, I suspect that you mistaken melspectrogram/filterbank for MFCC. Because as far as I understand you use IDFT only for MFCC. So python_speech_features.fbank should be the same...

To this you can add `platform :ios, '14.0'` in Podfile under section `target 'myapp' do`

Still with latest version this does not work out of the box