def test_created_net_has_correct_layer_sizes(self):
nnet = NeuralNet.create_from_file(fname=self.test_file)
self.assertEqual(nnet.layer_sizes(), self.net_params['layer_sizes'])
net_params = {
'layer_sizes': [1, 1, 1],
'layers': [{
'weights': [[3]],
'biases': [5]
}, {
'weights': [[1]],
'biases': [1]
}]
}
self.make_temp_params_file(net_params)
nnet = NeuralNet.create_from_file(fname=self.test_file)
self.assertEqual(nnet.layer_sizes(), self.net_params['layer_sizes'])
def test_created_net_biases(self):
nnet = NeuralNet.create_from_file(fname=self.test_file)
biases = nnet.biases()
expected_biases1 = self.net_params['layers'][0]['biases']
expected_biases2 = self.net_params['layers'][1]['biases']
self.assertEqual(biases[0].tolist(), expected_biases1)
self.assertEqual(biases[1].tolist(), expected_biases2)
def test_created_net_weights(self):
nnet = NeuralNet.create_from_file(fname=self.test_file)
weights = nnet.weights()
expected_weights1 = self.net_params['layers'][0]['weights']
expected_weights2 = self.net_params['layers'][1]['weights']
self.assertEqual(weights[0].tolist(), expected_weights1)
self.assertEqual(weights[1].tolist(), expected_weights2)
def test_costs_match(self):
nnet = NetFactory.create_neural_net(sizes=[2, 3, 1, 10, 2])
nnet.randomize_parameters()
cost_func = CrossEntropyCost(nnet)
X = [np.array([90, 23], float), np.array([0, 2], float)]
Y = [np.array([0.4, 0.6], float), np.array([0.3, 0])]
examples = PreloadSource((X, Y))
c1 = cost_func.get_cost(examples)
fname = os.path.join('test_temp', 'nets_params.json')
nnet.save(dest_fname=fname)
nnet = NeuralNet.create_from_file(fname)
c2 = cost_func.get_cost(examples)
self.assertAlmostEqual(c1, c2, places=4)
def test_for_net_with_multiple_hidden_layers(self):
net_params = {
'layer_sizes': [1, 1, 1, 2],
'layers': [{
'weights': [[3]],
'biases': [5]
}, {
'weights': [[1]],
'biases': [1]
}, {
'weights': [[1.5], [3]],
'biases': [10, 20]
}]
}
self.make_temp_params_file(net_params)
nnet = NeuralNet.create_from_file(fname=self.test_file)
weights = nnet.weights()
biases = nnet.biases()
self.assertEqual(nnet.layer_sizes(), self.net_params['layer_sizes'])
expected_weights1 = self.net_params['layers'][0]['weights']
expected_weights2 = self.net_params['layers'][1]['weights']
expected_weights3 = self.net_params['layers'][2]['weights']
self.assertEqual(weights[0].tolist(), expected_weights1)
self.assertEqual(weights[1].tolist(), expected_weights2)
self.assertEqual(weights[2].tolist(), expected_weights3)
expected_biases1 = self.net_params['layers'][0]['biases']
expected_biases2 = self.net_params['layers'][1]['biases']
expected_biases3 = self.net_params['layers'][2]['biases']
self.assertEqual(biases[0].tolist(), expected_biases1)
self.assertEqual(biases[1].tolist(), expected_biases2)
self.assertEqual(biases[2].tolist(), expected_biases3)
def step(context, fname):
context.new_net = NeuralNet.create_from_file(fname)
def test_returns_neural_net(self):
nnet = NeuralNet.create_from_file(fname=self.test_file)
self.assertIsInstance(nnet, NeuralNet)
