Takeo Shibata

I know the sample code is described here https://trix-editor.org/js/attachments.js But is there any way we can submit the attached file togather with trix-editor content? I see main text and associated...

I know fer2013 is 48 x 48 pixel data https://github.com/oarriaga/face_classification I try to convert my own jpg file to pixcel as fer2013. https://stackoverflow.com/questions/43416114/how-to-convert-images-to-pixels-values-and-store-them-in-a-text-file ``` from PIL import Image import numpy...

03_05_vae_faces_train Error durinig training

8

I try to run this on Google Colab (TF 2.3) (Branch=tensorflow_2) I downloaded the image from https://www.kaggle.com/jessicali9530/celeba-dataset and only placed about 1000 jpg files and changed epoch to 10 from...

Any recipe on LIBRISPEECH?

2

Thank you for sharing this valuable info. I read http://www.merl.com/publications/docs/TR2019-100.pdf I am wondering if there is recipe for librispeech (The data_prep.sh seems to be very specific for WSJ curpos) Regards

In colab sample, https://colab.research.google.com/drive/1e9o2NB2GDDjadptGr3rwQwTcw-IrFOnm The model downloaded trained by "wavegan.py train" or "specgan.py train"? After I execute training by train_wavegan.py train ./train --data_dir ./wavedatadir I see some audio generated then...

How to generate wav sample from trained chpt files v2, I cannot find object 'z:0' and 'G_z_spec:0'

1

For Sample model trained by V1 and downloaded from https://s3.amazonaws.com/wavegan-v1/models I can see the tensor object Tensor("z:0", shape=(?, 100), dtype=float32) as well as 'G_z:0' and 'G_z_spec:0' Thus I can execute...

extra.yaml for task1b.py stoped with error "AttributeError: 'FeatureContainer' object has no attribute 'sequence_axis'"

1

I try the extra.yaml for example 2 or 3. ``` python task1b.py -p extra.yaml ``` then I got ``` [I] Collecting training data [E] Uncaught exception (logging.py:221) Traceback (most recent...