zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-06-24 09:21:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix and update binary cross entropy loss tests (#133)

Browse Source 
* fix conflicts

* updated tests
This commit is contained in:
__mo_san__ 2023-12-11 21:42:17 +01:00 committed by GitHub
parent e080290ba4
commit 072044e28f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 56 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
python/tests/test_nn.py
View File

@ -101,13 +101,28 @@ class TestNN(mlx_tests.MLXTestCase):
self.assertTrue(mx.allclose(losses_sum, expected_sum)) self.assertTrue(mx.allclose(losses_sum, expected_sum))
def test_binary_cross_entropy(self): def test_binary_cross_entropy(self):
inputs = mx.array([[0.5, 0.5], [0.5, 0.5]]) inputs = mx.array([[0.5, 0.5, 0.2, 0.9], [0.1, 0.3, 0.5, 0.5]])
targets = mx.array([[0.0, 1.0], [1.0, 0.0]]) targets = mx.array([[0.0, 1.0, 0.0, 1.0], [1.0, 0.0, 1.0, 0.0]])
# Test with reduction 'none' # Test with reduction 'none'
losses_none = nn.losses.binary_cross_entropy(inputs, targets, reduction="none") losses_none = nn.losses.binary_cross_entropy(inputs, targets, reduction="none")
expected_none = mx.array([[0.693147, 0.693147], [0.693147, 0.693147]]) expected_none = mx.array(
self.assertTrue(mx.allclose(losses_none, expected_none)) [
[
0.6931471824645996,
0.6931471824645996,
0.2231435477733612,
0.10536054521799088,
],
[
2.3025851249694824,
0.3566749691963196,
0.6931471824645996,
0.6931471824645996,
],
]
)
self.assertTrue(mx.allclose(losses_none, expected_none, rtol=1e-5, atol=1e-8))
# Test with reduction 'mean' # Test with reduction 'mean'
losses_mean = nn.losses.binary_cross_entropy(inputs, targets, reduction="mean") losses_mean = nn.losses.binary_cross_entropy(inputs, targets, reduction="mean")
@ -119,6 +134,43 @@ class TestNN(mlx_tests.MLXTestCase):
expected_sum = mx.sum(expected_none) expected_sum = mx.sum(expected_none)
self.assertTrue(mx.allclose(losses_sum, expected_sum)) self.assertTrue(mx.allclose(losses_sum, expected_sum))
def test_bce_loss_module(self):
inputs = mx.array([[0.5, 0.5, 0.2, 0.9], [0.1, 0.3, 0.5, 0.5]])
targets = mx.array([[0.0, 1.0, 0.0, 1.0], [1.0, 0.0, 1.0, 0.0]])
# Test with reduction 'none'
loss_module_none = nn.losses.BCELoss(reduction="none")
losses_none = loss_module_none(inputs, targets)
expected_none = mx.array(
[
[
0.6931471824645996,
0.6931471824645996,
0.2231435477733612,
0.10536054521799088,
],
[
2.3025851249694824,
0.3566749691963196,
0.6931471824645996,
0.6931471824645996,
],
]
)
self.assertTrue(mx.allclose(losses_none, expected_none, rtol=1e-5, atol=1e-8))
# Test with reduction 'mean'
loss_module_mean = nn.losses.BCELoss(reduction="mean")
losses_mean = loss_module_mean(inputs, targets)
expected_mean = mx.mean(expected_none)
self.assertTrue(mx.allclose(losses_mean, expected_mean))
# Test with reduction 'sum'
loss_module_sum = nn.losses.BCELoss(reduction="sum")
losses_sum = loss_module_sum(inputs, targets)
expected_sum = mx.sum(expected_none)
self.assertTrue(mx.allclose(losses_sum, expected_sum))
def test_gelu(self): def test_gelu(self):
inputs = [1.15286231, -0.81037411, 0.35816911, 0.77484438, 0.66276414] inputs = [1.15286231, -0.81037411, 0.35816911, 0.77484438, 0.66276414]