mnist_dnn_spikey Namespace Reference

Variables
int	batch_size = 128
int	num_classes = 10
int	epochs = 25
	x_test = x_test.reshape(10000, 28,28,1)
	y_test = keras.utils.to_categorical(y_test, num_classes)
	x_train = x_train.reshape(60000,28,28,1)
	y_train = keras.utils.to_categorical(y_train, num_classes)
	x_train_new = x_train
	new_im = np.zeros((14,14)) for i in range(0,28,2): for j in range(0,28,2): x_train_new[counter][int(i/2)][int(j/2)] = (image[i][j] + image[i+1][j] + image[i][j+1] + image[i+1][j+1])/4.0 x_train_new.append(new_im) More...
	x_test_new = x_test
	model = Sequential()
	loss
	optimizer
	metrics
	history
	score = model.evaluate(x_test_new, y_test, verbose=0)
	json_string = model.to_json()

Detailed Description

Trains a simple deep NN on the downscaled MNIST dataset.
Adapted from 
https://raw.githubusercontent.com/keras-team/keras/master/examples/mnist_mlp.py

Variable Documentation

int mnist_dnn_spikey.batch_size = 128

Definition at line 18 of file mnist_dnn_spikey.py.

int mnist_dnn_spikey.epochs = 25

Definition at line 20 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.history

Initial value:

= model.fit(x_train_new, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_data=(x_test_new, y_test))

Definition at line 78 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.json_string = model.to_json()

Definition at line 89 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.loss

Definition at line 74 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.metrics

Definition at line 76 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.model = Sequential()

Definition at line 61 of file mnist_dnn_spikey.py.

int mnist_dnn_spikey.num_classes = 10

Definition at line 19 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.optimizer

Definition at line 75 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.score = model.evaluate(x_test_new, y_test, verbose=0)

Definition at line 83 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.x_test = x_test.reshape(10000, 28,28,1)

Definition at line 23 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.x_test_new = x_test

Definition at line 59 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.x_train = x_train.reshape(60000,28,28,1)

Definition at line 25 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.x_train_new = x_train

new_im = np.zeros((14,14)) for i in range(0,28,2): for j in range(0,28,2): x_train_new[counter][int(i/2)][int(j/2)] = (image[i][j] + image[i+1][j] + image[i][j+1] + image[i+1][j+1])/4.0 x_train_new.append(new_im)

new_im = np.zeros((14,14)) for i in range(0,28,2): for j in range(0,28,2): x_test_new[counter][int(i/2)][int(j/2)] = (image[i][j] + image[i+1][j] + image[i][j+1] + image[i+1][j+1])/4.0 x_test_new.append(new_im)

Definition at line 58 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.y_test = keras.utils.to_categorical(y_test, num_classes)

Definition at line 23 of file mnist_dnn_spikey.py.

mnist_dnn_spikey.y_train = keras.utils.to_categorical(y_train, num_classes)

Definition at line 35 of file mnist_dnn_spikey.py.