Python torch.testing() Examples

The following are 8 code examples of torch.testing(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module torch , or try the search function .
Example #1
Source File: transforms_test.py    From asteroid with MIT License 6 votes vote down vote up 
def test_to_numpy(np_torch_tuple, dim):
    """ Test torch --> np conversion (right angles)"""
    from_np, from_torch = np_torch_tuple
    if dim == 0:
        np_array = np.array(from_np)
        torch_tensor = torch.tensor(from_torch)
    elif dim == 1:
        np_array = np.array([from_np])
        torch_tensor = torch.tensor([from_torch])
    elif dim == 2:
        np_array = np.array([[from_np]])
        torch_tensor = torch.tensor([[from_torch]])
    else:
        return
    np_from_torch = transforms.to_numpy(torch_tensor, dim=dim)
    np.testing.assert_allclose(np_array, np_from_torch)
Example #2
Source File: transforms_test.py    From asteroid with MIT License 6 votes vote down vote up 
def test_from_numpy(np_torch_tuple, dim):
    """ Test np --> torch conversion (right angles)"""
    from_np, from_torch = np_torch_tuple
    if dim == 0:
        np_array = np.array(from_np)
        torch_tensor = torch.tensor(from_torch)
    elif dim == 1:
        np_array = np.array([from_np])
        torch_tensor = torch.tensor([from_torch])
    elif dim == 2:
        np_array = np.array([[from_np]])
        torch_tensor = torch.tensor([[from_torch]])
    else:
        return
    torch_from_np = transforms.from_numpy(np_array, dim=dim)
    np.testing.assert_allclose(torch_tensor, torch_from_np)
Example #3
Source File: test_pooling.py    From flambe with MIT License 5 votes vote down vote up 
def test_last_pooling_with_mask():
    lp = pooling.LastPooling()
    out = lp(TENSOR, padding_mask=MASK)

    assert out.size() == torch.Size([2, 4])

    expected = Tensor(
        [
            [5, 6, 7, 8],
            [9, 10, 11, 12]
        ]
    )
    torch.testing.assert_allclose(out, expected)
Example #4
Source File: test_pooling.py    From flambe with MIT License 5 votes vote down vote up 
def test_first_pooling_with_mask():
    lp = pooling.FirstPooling()
    out = lp(TENSOR, padding_mask=MASK)

    assert out.size() == torch.Size([2, 4])

    expected = Tensor(
        [
            [1, 2, 3, 4],
            [1, 2, 3, 4]
        ]
    )
    torch.testing.assert_allclose(out, expected)
Example #5
Source File: test_pooling.py    From flambe with MIT License 5 votes vote down vote up 
def test_sum_pooling_with_mask():
    lp = pooling.SumPooling()
    out = lp(TENSOR, padding_mask=MASK)

    assert out.size() == torch.Size([2, 4])

    expected = Tensor(
        [
            [6, 8, 10, 12],
            [15, 18, 21, 24]
        ]
    )
    torch.testing.assert_allclose(out, expected)
Example #6
Source File: test_pooling.py    From flambe with MIT License 5 votes vote down vote up 
def test_avg_pooling_with_mask():
    lp = pooling.AvgPooling()
    out = lp(TENSOR, padding_mask=MASK)

    assert out.size() == torch.Size([2, 4])

    expected = Tensor(
        [
            [3, 4, 5, 6],
            [5, 6, 7, 8]
        ]
    )
    torch.testing.assert_allclose(out, expected)
Example #7
Source File: test_bases.py    From PyVideoResearch with GNU General Public License v3.0 5 votes vote down vote up 
def test_model_updates(inputs, model, target, whitelist=[]):
    args = Args()
    args.balanceloss = False
    args.window_smooth = 0
    criterion = default_criterion.DefaultCriterion(args)
    optimizer = torch.optim.SGD(model.parameters(), lr=1.)
    optimizer.zero_grad()
    params = list(model.named_parameters())
    initial_params = [(name, p.clone()) for (name, p) in params]
    output = model(inputs)
    meta = {}
    _, loss, _ = criterion(output, target, meta)
    loss.backward()
    optimizer.step()
    for (_, p0), (name, p1) in zip(initial_params, params):
        if name in whitelist:
            continue
        try:
            np.testing.assert_raises(AssertionError, torch.testing.assert_allclose, p0, p1)
        except AssertionError:
            if 'bias' in name:
                print('Warning: {} not updating'.format(name))
                continue
            if p1.grad.norm() > 1e-6:
                print('Warning: {} not significantly updating'.format(name))
                continue
            print('{} not updating'.format(name))
            for (nn1, pp1) in params:
                print('{} grad: {}'.format(nn1, pp1.grad.norm().item()))
            import pdb
            pdb.set_trace()
            raise
Example #8
Source File: transforms_test.py    From asteroid with MIT License 5 votes vote down vote up 
def test_return_ticket_np_torch(dim):
    """ Test torch --> np --> torch --> np conversion"""
    max_tested_ndim = 4
    # Random tensor shape
    tensor_shape = [random.randint(1, 10) for _ in range(max_tested_ndim)]
    # Make sure complex dimension has even shape
    tensor_shape[dim] = 2 * tensor_shape[dim]
    complex_tensor = torch.randn(tensor_shape)
    np_array = transforms.to_numpy(complex_tensor, dim=dim)
    tensor_back = transforms.from_numpy(np_array, dim=dim)
    np_back = transforms.to_numpy(tensor_back, dim=dim)
    # Check torch --> np --> torch
    assert_allclose(complex_tensor, tensor_back)
    # Check np --> torch --> np
    np.testing.assert_allclose(np_array, np_back)