Sparse_autoencoder
Sparse_autoencoder copied to clipboard
Implementing sparse autoencoder for MNIST data classification using keras and tensorflow
Hi jadhav, The code line "train_step = optimizer.minimize(cost, var_list=weight_list)" of the **sparseae_generic.py** file throws this error: _ValueError: `tape` is required when a `Tensor` loss is passed_ Cost variable is surely...
I am trying your model in this link {https://github.com/jadhavhninad/Sparse_autoencoder/blob/master/se_keras4.py} It gives me *(NAN) or very high loss Any advise ?
Hello, Is there a way to look at the latent space?