Skip to content

Instantly share code, notes, and snippets.

View seyedrezamirkhani's full-sized avatar

Reza Mirkhani seyedrezamirkhani

View GitHub Profile
@seyedrezamirkhani
seyedrezamirkhani / computation.py
Created October 21, 2019 11:05 — forked from AFAgarap/computation.py
Training procedure for a vanilla autoencoder model.
autoencoder = Autoencoder(intermediate_dim=64, original_dim=784)
opt = tf.optimizers.Adam(learning_rate=learning_rate)
(training_features, _), (test_features, _) = tf.keras.datasets.mnist.load_data()
training_features = training_features / np.max(training_features)
training_features = training_features.reshape(training_features.shape[0],
training_features.shape[1] * training_features.shape[2])
training_features = training_features.astype('float32')
training_dataset = tf.data.Dataset.from_tensor_slices(training_features)
training_dataset = training_dataset.batch(batch_size)