def test_div():
a = Tensor.randn(30, 40, requires_grad=True).to(Device.GPU)
b = Tensor.randn(30, 40, requires_grad=True).to(Device.GPU)
a_torch, b_torch = create_identical_torch_tensor(a, b)
c = a / b
c_torch = a_torch / b_torch
c.backward()
c_torch.sum().backward()
check_val_and_grad(a, a_torch)
check_val_and_grad(b, b_torch)
check_val_and_grad(c, c_torch)
def test_mul_broadcast():
a = Tensor.randn(3, 1, 3, requires_grad=True)
b = Tensor.randn(3, 1, 1, requires_grad=True)
a_torch, b_torch = create_identical_torch_tensor(a, b)
c = a * b
c_torch = a_torch * b_torch
c.backward()
c_torch.sum().backward()
check_val_and_grad(a, a_torch)
check_val_and_grad(b, b_torch)
check_val_and_grad(c, c_torch)
def test_matmul():
a = Tensor.randn(3, 4, requires_grad=True)
b = Tensor.randn(4, 2, requires_grad=True)
a_torch, b_torch = create_identical_torch_tensor(a, b)
c = a @ b
c_torch = a_torch @ b_torch
c.backward()
c_torch.sum().backward()
check_val_and_grad(a, a_torch)
check_val_and_grad(b, b_torch)
check_val_and_grad(c, c_torch)
def test_neg():
a = Tensor.randn(30, 40, requires_grad=True).to(Device.GPU)
a_torch = create_identical_torch_tensor(a)
b = -a
b_torch = -a_torch
b.backward()
b_torch.sum().backward()
check_val_and_grad(a, a_torch)
check_val_and_grad(b, b_torch)
def test_tanh():
a = Tensor.randn(20, 20, requires_grad=True)
a_torch = create_identical_torch_tensor(a)
b = a.tanh()
b_torch = a_torch.tanh()
b.backward()
b_torch.sum().backward()
check_val_and_grad(a, a_torch)
check_val_and_grad(b, b_torch)
def test_multiple():
a = Tensor.randn(2, 3, requires_grad=True)
b = Tensor.randn(2, 3, requires_grad=True)
a_torch, b_torch = create_identical_torch_tensor(a, b)
c = a / b
c_torch = a_torch / b_torch
d = a - b
d_torch = a_torch - b_torch
e = c + d
e_torch = c_torch + d_torch
e.backward()
e_torch.sum().backward()
check_val_and_grad(a, a_torch)
check_val_and_grad(b, b_torch)
check_val_and_grad(c, c_torch)
check_val_and_grad(d, d_torch)
check_val_and_grad(e, e_torch)
