def primitiv_test2(self): dev = D.Naive() Device.set_default(dev) g = Graph() Graph.set_default(g) x = F.input(np.array([[1], [2]])) a = F.input(np.array([[1, 2], [1, 2]])) y = F.matmul(a, x) return y.to_list()
def test_node_pow(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(np.isclose((x ** y).to_ndarrays()[0], np.array([[1, 2], [81, 65536]])).all()) self.assertTrue(np.isclose((x ** 2).to_ndarrays()[0], np.array([[1, 4], [9, 16]])).all()) self.assertTrue(np.isclose((2 ** x).to_ndarrays()[0], np.array([[2, 4], [8, 16]])).all()) self.assertTrue(np.isclose((x ** -2).to_ndarrays()[0], np.array([[1, 1/4], [1/9, 1/16]])).all()) input_arr = np.array([1, -1, 3, -3, 5, -5]) x = F.input(input_arr) self.assertTrue(((x ** 6).to_ndarrays()[0] == np.array([1, 1, 729, 729, 15625, 15625])).all()) self.assertTrue(((x ** 9).to_ndarrays()[0] == np.array([1, -1, 19683, -19683, 1953125, -1953125])).all()) input_arr = np.array([1, -1]) x = F.input(input_arr) self.assertTrue(((x ** 0x7fffffff).to_ndarrays()[0] == np.array([1, -1])).all()) self.assertTrue(((x ** -0x80000000).to_ndarrays()[0] == np.array([1, 1])).all()) self.assertRaises(TypeError, lambda: pow(x, y, 2))
def test_functions_input_argument(self): # list[ndarray] w/o shape x = F.input(self.ndarray_data) self.assertEqual(x.to_list(), self.list_data) self.assertEqual(x.shape(), Shape([4, 3], 2)) # ndarray w/o shape x = F.input(self.ndarray_data[0]) self.assertEqual(x.to_list(), self.list_data[:12]) self.assertEqual(x.shape(), Shape([4, 3], 1)) # list[float] w/o shape self.assertRaises(TypeError, lambda: F.input(self.list_data)) # list[float] w/ shape x = F.raw_input(Shape([4, 3], 2), self.list_data) self.assertEqual(x.to_list(), self.list_data) self.assertEqual(x.shape(), Shape([4, 3], 2))
def primitiv_test1(self): dev = D.Naive() Device.set_default(dev) g = Graph() Graph.set_default(g) x = F.input(np.array([[1], [2], [3]])) y = 2 * x + 3 return y.to_list()
def make_graph(inputs, train): x = F.input(inputs) w1 = F.parameter(pw1) b1 = F.parameter(pb1) h = F.relu(w1 @ x + b1) h = F.dropout(h, .5, train) w2 = F.parameter(pw2) b2 = F.parameter(pb2) return w2 @ h + b2
def make_graph(inputs): # We first store input values explicitly on GPU 0. x = F.input(inputs, device=dev0) w1 = F.parameter(pw1) b1 = F.parameter(pb1) w2 = F.parameter(pw2) b2 = F.parameter(pb2) # The hidden layer is calculated and implicitly stored on GPU 0. h_on_gpu0 = F.relu(w1 @ x + b1) # `copy()` transfers the hiddne layer to GPU 1. h_on_gpu1 = F.copy(h_on_gpu0, dev1) # The output layer is calculated and implicitly stored on GPU 1. return w2 @ h_on_gpu1 + b2
def make_graph(inputs, train): # Input and parameters. #x = F.input(Shape([IMAGE_HEIGHT, IMAGE_WIDTH], BATCH_SIZE), inputs) x = F.input(inputs) w_cnn1 = F.parameter(pw_cnn1) w_cnn2 = F.parameter(pw_cnn2) w_fc1 = F.parameter(pw_fc1) w_fc2 = F.parameter(pw_fc2) b_fc1 = F.parameter(pb_fc1) b_fc2 = F.parameter(pb_fc2) # CNNs h_cnn1 = F.relu(F.conv2d(x, w_cnn1, PADDING1, PADDING1, 1, 1, 1, 1)) h_pool1 = F.max_pool2d(h_cnn1, 2, 2, 0, 0, 2, 2) h_cnn2 = F.relu( F.conv2d(h_pool1, w_cnn2, PADDING2, PADDING2, 1, 1, 1, 1)) h_pool2 = F.max_pool2d(h_cnn2, 2, 2, 0, 0, 2, 2) # FC layers x_fc = F.dropout(F.flatten(h_pool2), .5, train) h_fc = F.dropout(F.relu(F.matmul(w_fc1, x_fc) + b_fc1), .5, train) return F.matmul(w_fc2, h_fc) + b_fc2
def test_node_mul(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(((x * y).to_ndarrays()[0] == np.array([[1, 2], [12, 32]])).all()) self.assertTrue(((x * 2).to_ndarrays()[0] == np.array([[2, 4], [6, 8]])).all()) self.assertTrue(((2 * x).to_ndarrays()[0] == np.array([[2, 4], [6, 8]])).all())
def primitiv_xor_test(self): dev = D.Naive() Device.set_default(dev) g = Graph() Graph.set_default(g) input_data = [ np.array([[1], [1]]), np.array([[-1], [1]]), np.array([[-1], [-1]]), np.array([[1], [-1]]), ] label_data = [ np.array([1]), np.array([-1]), np.array([1]), np.array([-1]), ] N = 8 pw = Parameter([1, N], I.XavierUniform()) pb = Parameter([], I.Constant(0)) pu = Parameter([N, 2], I.XavierUniform()) pc = Parameter([N], I.Constant(0)) if os.path.isfile('output/xor/pw.data') and os.path.isfile( 'output/xor/pb.data') and os.path.isfile( 'output/xor/pu.data') and os.path.isfile( 'output/xor/pc.data'): pw.load('output/xor/pw.data') pb.load('output/xor/pb.data') pu.load('output/xor/pu.data') pc.load('output/xor/pc.data') optimizer = O.SGD(0.01) optimizer.add(pw, pb, pu, pc) for epoch in range(1000): print(epoch, end=' ') g.clear() x = F.input(input_data) w = F.parameter(pw) b = F.parameter(pb) u = F.parameter(pu) c = F.parameter(pc) h = F.tanh(u @ x + c) y = F.tanh(w @ h + b) for val in y.to_list(): print('{:+.6f},'.format(val), end=' ') loss = self.calc_loss(y, label_data) print('loss={:.6f}'.format(loss.to_float())) optimizer.reset_gradients() loss.backward() optimizer.update() pw.save('output/xor/pw.data') pb.save('output/xor/pb.data') pu.save('output/xor/pu.data') pc.save('output/xor/pc.data') return y.to_list()
def calc_loss(self, y, label_data): t = F.input(label_data) diff = y - t return F.batch.mean(diff * diff)
def test_node_truediv(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(((x / y).to_ndarrays()[0] == np.array([[1, 2], [0.75, 0.5]])).all()) self.assertTrue(((x / 2).to_ndarrays()[0] == np.array([[0.5, 1], [1.5, 2]])).all()) self.assertTrue(((2 / y).to_ndarrays()[0] == np.array([[2, 2], [0.5, 0.25]])).all())
def test_node_matmul(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(((x @ y).to_ndarrays()[0] == np.array([[9, 17], [19, 35]])).all()) self.assertRaises(TypeError, lambda: x @ 2) self.assertRaises(TypeError, lambda: 2 @ x)
def main(): dev = D.Naive() # or D.CUDA(gpuid) Device.set_default(dev) # Parameters pw1 = Parameter([8, 2], I.XavierUniform()) pb1 = Parameter([8], I.Constant(0)) pw2 = Parameter([1, 8], I.XavierUniform()) pb2 = Parameter([], I.Constant(0)) # Optimizer optimizer = O.SGD(0.1) # Registers parameters. optimizer.add(pw1, pb1, pw2, pb2) # Training data input_data = [ np.array([1, 1], dtype=np.float32), # Sample 1 np.array([1, -1], dtype=np.float32), # Sample 2 np.array([-1, 1], dtype=np.float32), # Sample 3 np.array([-1, -1], dtype=np.float32), # Sample 4 ] output_data = [ np.array([1], dtype=np.float32), # Label 1 np.array([-1], dtype=np.float32), # Label 2 np.array([-1], dtype=np.float32), # Label 3 np.array([1], dtype=np.float32), # Label 4 ] g = Graph() Graph.set_default(g) for i in range(10): g.clear() # Builds a computation graph. x = F.input(input_data) w1 = F.parameter(pw1) b1 = F.parameter(pb1) w2 = F.parameter(pw2) b2 = F.parameter(pb2) h = F.tanh(w1 @ x + b1) y = w2 @ h + b2 # Obtains values. y_val = y.to_list() print("epoch ", i, ":") for j in range(4): print(" [", j, "]: ", y_val[j]) # Extends the computation graph to calculate loss values. t = F.input(output_data) diff = t - y loss = F.batch.mean(diff * diff) # Obtains the loss. loss_val = loss.to_float() print(" loss: ", loss_val) # Updates parameters. optimizer.reset_gradients() loss.backward() optimizer.update()
def test_node_sub(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(((x - y).to_ndarrays()[0] == np.array([[0, 1], [-1, -4]])).all()) self.assertTrue(((x - 2).to_ndarrays()[0] == np.array([[-1, 0], [1, 2]])).all()) self.assertTrue(((2 - x).to_ndarrays()[0] == np.array([[1, 0], [-1, -2]])).all())
def test_node_add(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(((x + y).to_ndarrays()[0] == np.array([[2, 3], [7, 12]])).all()) self.assertTrue(((x + 2).to_ndarrays()[0] == np.array([[3, 4], [5, 6]])).all()) self.assertTrue(((2 + x).to_ndarrays()[0] == np.array([[3, 4], [5, 6]])).all())
def test_node_neg(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(((-x).to_ndarrays()[0] == -self.a).all())
def test_node_pos(self): x = F.input(self.a) y = F.input(self.b) self.assertTrue(((+x).to_ndarrays()[0] == self.a).all())
def test_input_ndarrays(self): x = F.input(self.input_data) self.assertEqual(x.to_list(), self.list_expected) self.assertTrue((x.to_ndarrays()[0] == self.input_data[0]).all()) self.assertTrue((x.to_ndarrays()[1] == self.input_data[1]).all())