Deep-Learning-Experiments
Deep-Learning-Experiments copied to clipboard
roatienza
Videos, notes and experiments to understand deep learning
Added a resources on the various type of CNN that have been developed. The article discusses the architecture and results of the models.
Implemented the exact same idea, with more readable less error-prone code. Per: https://towardsdatascience.com/gan-by-example-using-keras-on-tensorflow-backend-1a6d515a60d0
in `https://github.com/roatienza/Deep-Learning-Experiments/blob/master/Experiments/Tensorflow/GAN/dcgan_mnist.py` you compute the generator loss as: `a_loss = self.adversarial.train_on_batch(noise, y)` but this also trains the discriminator using only the fake samples. shouldn't you freeze the discriminator weights for...
Fixed two non-deterministic sources of hard-to-catch issues in RNN example.
How long does it take to run 10K iterations on a 2.7 GHZ intel Core i5 processor Mac book? I was at 150 iterations after so many hours? Is there...
I was trying to implement https://github.com/roatienza/Deep-Learning-Experiments/blob/master/Experiments/Tensorflow/GAN/dcgan_mnist.py and it works fine. But I tried the exact same code without the wrapper class ie I wrote just one class DCGAN and tried...
How to use the Trained GAN model to generate digit images?
AttributeError Traceback (most recent call last) in () 190 191 if __name__ == '__main__': --> 192 mnist_dcgan = MNIST_DCGAN() 193 timer = ElapsedTimer() 194 mnist_dcgan.train(train_steps=10000, batch_size=256, save_interval=500) in __init__(self) 135...
When i use cifar 10 as input to the same code, i get this error ValueError: number of input channels does not match corresponding dimension of filter, 1 != 3
