Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix: Preserve input dtype in Dropout layer output #1323

Merged
merged 3 commits into from
Aug 13, 2024
Merged

Fix: Preserve input dtype in Dropout layer output #1323

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7b1fad5
Fix: Preserve input dtype in Dropout layer output
bhargavyagnik Aug 13, 2024
089dfda
Update test cases in test_nn.py
bhargavyagnik Aug 13, 2024
9c872ab
updated dropout.py
bhargavyagnik Aug 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions python/mlx/nn/layers/dropout.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ def __call__(self, x):

mask = mx.random.bernoulli(self._p_1, x.shape)

return (1 / self._p_1) * mask * x
return (mask * x) * (1 / self._p_1)


class Dropout2d(Module):
Expand Down Expand Up @@ -85,7 +85,7 @@ def __call__(self, x):
mask_shape[-2] = mask_shape[-3] = 1

mask = mx.random.bernoulli(p=self._p_1, shape=mask_shape)
return (1 / self._p_1) * mask * x
return (mask * x) * (1 / self._p_1)


class Dropout3d(Module):
Expand Down Expand Up @@ -134,4 +134,4 @@ def __call__(self, x):
mask_shape[-2] = mask_shape[-3] = mask_shape[-4] = 1

mask = mx.random.bernoulli(p=self._p_1, shape=mask_shape)
return (1 / self._p_1) * mask * x
return (mask * x) * (1 / self._p_1)
52 changes: 26 additions & 26 deletions python/tests/test_nn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -939,73 +939,73 @@ def test_rope(self):
shape = (1, 3, 4)
x = mx.random.uniform(shape=shape)
y = rope(x)
self.assertTrue(y.shape, shape)
self.assertTrue(y.dtype, mx.float32)
self.assertEqual(y.shape, shape)
self.assertEqual(y.dtype, mx.float32)

y = rope(x, offset=3)
self.assertTrue(y.shape, shape)
self.assertEqual(y.shape, shape)

y = rope(x.astype(mx.float16))
self.assertTrue(y.dtype, mx.float16)
self.assertEqual(y.dtype, mx.float16)

def test_alibi(self):
alibi = nn.ALiBi()
shape = [1, 8, 20, 20]
shape = (1, 8, 20, 20)
x = mx.random.uniform(shape=shape)
y = alibi(x)
self.assertTrue(y.shape, shape)
self.assertTrue(y.dtype, mx.float32)
self.assertEqual(y.shape, shape)
self.assertEqual(y.dtype, mx.float32)

y = alibi(x.astype(mx.float16))
self.assertTrue(y.dtype, mx.float16)
self.assertEqual(y.dtype, mx.float16)

def test_dropout(self):
x = mx.ones((2, 4))
y = nn.Dropout(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.float32)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.float32)

x = mx.ones((2, 4), dtype=mx.bfloat16)
y = nn.Dropout(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.bfloat16)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.bfloat16)

x = mx.ones((2, 4), dtype=mx.float16)
y = nn.Dropout(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.float16)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.float16)

def test_dropout2d(self):
x = mx.ones((2, 4, 4, 4))
y = nn.Dropout2d(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.float32)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.float32)

x = mx.ones((2, 4, 4, 4), dtype=mx.bfloat16)
y = nn.Dropout2d(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.bfloat16)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.bfloat16)

x = mx.ones((2, 4, 4, 4), dtype=mx.float16)
y = nn.Dropout2d(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.float16)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.float16)

def test_dropout3d(self):
x = mx.ones((2, 4, 4, 4, 4))
y = nn.Dropout3d(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.float32)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.float32)

x = mx.ones((2, 4, 4, 4, 4), dtype=mx.bfloat16)
y = nn.Dropout3d(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.bfloat16)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.bfloat16)
Comment on lines +1002 to +1003
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for fixing those!!


x = mx.ones((2, 4, 4, 4, 4), dtype=mx.float16)
y = nn.Dropout3d(0.5)(x)
self.assertTrue(y.shape, x.shape)
self.assertTrue(y.dtype, mx.float16)
self.assertEqual(y.shape, x.shape)
self.assertEqual(y.dtype, mx.float16)

def test_upsample(self):
b, h, w, c = 1, 2, 2, 1
Expand Down