GDL_code
GDL_code copied to clipboard
davidADSP
The official code repository for examples in the O'Reilly book 'Generative Deep Learning'
I got the GDL source to compile on a fairly plain-vanilla Ubuntu 18.04 system, but only after solving some loader problems with unresolved names, in particular "pj_init_plus" --- this name...
What is the best way to configure your notebooks to utilize GPU Hardware?
Hi there, Training the _05_01_cyclegan_ notebook (apple2orange) is taking me ~30 hours on a system with a 2060RTX Super. Is anyone else having similar (large) training times? I tried Google...
Add this at the end of /models/layers/layers.py def get_config(self): config = super().get_config().copy() config.update({ 'padding': self.padding, 'input_spec': self.input_spec, }) return config
This occurs in 03_01 AutoEncoder_Train and 03_03_vae_digits_train. Running on Windows 10 using python 3.6
`models/layers/layers.py` imports `keras.backend as K` but does not use it.
ValueError: Invalid class_mode: other; expected one of: {'raw', 'input', 'binary', 'categorical', None, 'multi_output', 'sparse'} https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator#flow_from_dataframe
ValueError: Invalid class_mode: other; expected one of: {'raw', 'input', 'binary', 'categorical', None, 'multi_output', 'sparse'} https://keras.io/preprocessing/image/
I am referring to [this script](https://github.com/davidADSP/GDL_code/blob/tensorflow_2/models/WGAN.py). After compiling the GAN, the critic's been set to trainable again. Could you explain why that might be? Most of the vanilla DCGANs suggest...
Hi I've read halfway through your awesome book and now want to start diving into the code. Unfortunately, I cannot get past setting things up. After running 'pip install requirements'...
