def solver(self, load_from_file=True):
for acti_fn in ['relu', 'sigmoid', 'linear', 'tanh']:
if (load_from_file == False):
model = Q1.MyNeuralNetwork(5, [784, 256, 128, 64, 10], acti_fn,
0.1, 'normal', 500, 100)
model.fill_testing_data(self.X_test, self.y_test, verbose=1)
print('-------' * 8)
print('Begening fit for activation function', acti_fn)
model.fit(self.X_train, self.y_train)
joblib.dump(model, 'models/saved_model_' + acti_fn)
else:
model = joblib.load('models/saved_model_' + acti_fn)
err = model.get_errors_featres()
self.__plot_errorVSepochs(err[0], err[1],
'Actvation function = ' + acti_fn)
NNfeatures = TSNE(n_components=2).fit_transform(err[2])
self.__plot_cluster(NNfeatures, self.y_test,
'Features using ' + acti_fn)
print('Accuracy for', acti_fn, '= ',
model.score(self.X_test, self.y_test) * 100, '%')
import matplotlib.pylab as plt
train_x, train_y = loadlocal_mnist("data/train-images.idx3-ubyte",
"data/train-labels.idx1-ubyte")
test_x, test_y = loadlocal_mnist("data/t10k-images.idx3-ubyte",
"data/t10k-labels.idx1-ubyte")
train_x = preprocessing.normalize(train_x)
test_x = preprocessing.normalize(test_x)
enc = OneHotEncoder(sparse=False, categories='auto')
train_y = enc.fit_transform(train_y.reshape(len(train_y), -1))
test_y = enc.transform(test_y.reshape(len(test_y), -1))
network = Q1.MyNeuralNetwork(n_layers=5,
layer_sizes=[784, 256, 128, 64, 10],
activation="relu",
learning_rate=0.1,
weight_init="normal",
batch_size=200,
num_epochs=101)
network.fit(network.train_x, network.train_y)
network.tsne()
network = Q1.MyNeuralNetwork(n_layers=5,
layer_sizes=[784, 256, 128, 64, 10],
activation="relu",
learning_rate=0.1,
weight_init="normal",
batch_size=200,
num_epochs=101)
network.fit(network.train_x, network.train_y)
network.saveModel(network, "ReLU_normal")