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

[xdoctest] reformat example code with google style No.102-104 #56124

Merged
merged 5 commits into from
Aug 16, 2023
Merged

[xdoctest] reformat example code with google style No.102-104 #56124

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7f43f82
fix: updated code examples.
PommesPeter Aug 9, 2023
5547c94
fix: updated blank lines.
PommesPeter Aug 10, 2023
d23b226
fix: updated code style
PommesPeter Aug 11, 2023
70be8c8
fix: removed extra changes
PommesPeter Aug 14, 2023
69cf041
fix: refine detail
PommesPeter Aug 14, 2023
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
67 changes: 34 additions & 33 deletions python/paddle/optimizer/adadelta.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,39 +70,40 @@ class Adadelta(Optimizer):
Examples:
.. code-block:: python

import paddle

inp = paddle.uniform([10, 10], dtype="float32", min=-0.1, max=0.1)
linear = paddle.nn.Linear(10, 10)
out = linear(inp)
loss = paddle.mean(out)
beta1 = paddle.to_tensor([0.9], dtype="float32")
beta2 = paddle.to_tensor([0.99], dtype="float32")
adadelta = paddle.optimizer.Adadelta(learning_rate=0.1, parameters=linear.parameters(), weight_decay=0.01)
back = out.backward()
adadelta.step()
adadelta.clear_grad()

#Note that the learning_rate of linear_2 is 0.01.
linear_1 = paddle.nn.Linear(10, 10)
linear_2 = paddle.nn.Linear(10, 10)
inp = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
out = linear_1(inp)
out = linear_2(out)
loss = paddle.mean(out)
adadelta = paddle.optimizer.Adadelta(
learning_rate=0.1,
parameters=[{
'params': linear_1.parameters()
}, {
'params': linear_2.parameters(),
'weight_decay': 0.001,
'learning_rate': 0.1,
}],
weight_decay=0.01)
out.backward()
adadelta.step()
adadelta.clear_grad()
>>> import paddle
>>> paddle.seed(2023)
PommesPeter marked this conversation as resolved.
Show resolved Hide resolved

>>> inp = paddle.uniform([10, 10], dtype="float32", min=-0.1, max=0.1)
>>> linear = paddle.nn.Linear(10, 10)
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> beta1 = paddle.to_tensor([0.9], dtype="float32")
>>> beta2 = paddle.to_tensor([0.99], dtype="float32")
>>> adadelta = paddle.optimizer.Adadelta(learning_rate=0.1, parameters=linear.parameters(), weight_decay=0.01)
>>> back = out.backward()
>>> adadelta.step()
>>> adadelta.clear_grad()

>>> # Note that the learning_rate of linear_2 is 0.01.
PommesPeter marked this conversation as resolved.
Show resolved Hide resolved
>>> linear_1 = paddle.nn.Linear(10, 10)
>>> linear_2 = paddle.nn.Linear(10, 10)
>>> inp = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
>>> out = linear_1(inp)
>>> out = linear_2(out)
>>> loss = paddle.mean(out)
>>> adadelta = paddle.optimizer.Adadelta(
... learning_rate=0.1,
... parameters=[{
... 'params': linear_1.parameters()
... }, {
... 'params': linear_2.parameters(),
... 'weight_decay': 0.001,
... 'learning_rate': 0.1,
... }],
... weight_decay=0.01)
>>> out.backward()
>>> adadelta.step()
>>> adadelta.clear_grad()

"""

Expand Down
65 changes: 33 additions & 32 deletions python/paddle/optimizer/adagrad.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,38 +70,39 @@ class Adagrad(Optimizer):
Examples:
.. code-block:: python

import paddle

inp = paddle.rand(shape=[10, 10])
linear = paddle.nn.Linear(10, 10)
out = linear(inp)
loss = paddle.mean(out)
adagrad = paddle.optimizer.Adagrad(learning_rate=0.1,
parameters=linear.parameters())
out.backward()
adagrad.step()
adagrad.clear_grad()

#Note that the learning_rate of linear_2 is 0.01.
linear_1 = paddle.nn.Linear(10, 10)
linear_2 = paddle.nn.Linear(10, 10)
inp = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
out = linear_1(inp)
out = linear_2(out)
loss = paddle.mean(out)
adagrad = paddle.optimizer.Adagrad(
learning_rate=0.1,
parameters=[{
'params': linear_1.parameters()
}, {
'params': linear_2.parameters(),
'weight_decay': 0.001,
'learning_rate': 0.1,
}],
weight_decay=0.01)
out.backward()
adagrad.step()
adagrad.clear_grad()
>>> import paddle
>>> paddle.seed(2023)

>>> inp = paddle.rand(shape=[10, 10])
>>> linear = paddle.nn.Linear(10, 10)
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> adagrad = paddle.optimizer.Adagrad(learning_rate=0.1,
... parameters=linear.parameters())
>>> out.backward()
>>> adagrad.step()
>>> adagrad.clear_grad()

>>> # Note that the learning_rate of linear_2 is 0.01.
PommesPeter marked this conversation as resolved.
Show resolved Hide resolved
>>> linear_1 = paddle.nn.Linear(10, 10)
>>> linear_2 = paddle.nn.Linear(10, 10)
>>> inp = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
>>> out = linear_1(inp)
>>> out = linear_2(out)
>>> loss = paddle.mean(out)
>>> adagrad = paddle.optimizer.Adagrad(
... learning_rate=0.1,
... parameters=[{
... 'params': linear_1.parameters()
... }, {
... 'params': linear_2.parameters(),
... 'weight_decay': 0.001,
... 'learning_rate': 0.1,
... }],
... weight_decay=0.01)
>>> out.backward()
>>> adagrad.step()
>>> adagrad.clear_grad()

"""
_moment_acc_str = "moment"
Expand Down
127 changes: 63 additions & 64 deletions python/paddle/optimizer/adam.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,63 +98,62 @@ class Adam(Optimizer):
.. code-block:: python
:name: code-example1

import paddle

linear = paddle.nn.Linear(10, 10)
inp = paddle.rand([10,10], dtype="float32")
out = linear(inp)
loss = paddle.mean(out)
adam = paddle.optimizer.Adam(learning_rate=0.1,
parameters=linear.parameters())
loss.backward()
adam.step()
adam.clear_grad()
>>> import paddle
>>> paddle.seed(2023)

>>> linear = paddle.nn.Linear(10, 10)
>>> inp = paddle.rand([10,10], dtype="float32")
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> adam = paddle.optimizer.Adam(learning_rate=0.1,
... parameters=linear.parameters())
>>> loss.backward()
>>> adam.step()
>>> adam.clear_grad()

.. code-block:: python
:name: code-example2

# Adam with beta1/beta2 as Tensor and weight_decay as float
import paddle

linear = paddle.nn.Linear(10, 10)
inp = paddle.rand([10,10], dtype="float32")
out = linear(inp)
loss = paddle.mean(out)

beta1 = paddle.to_tensor([0.9], dtype="float32")
beta2 = paddle.to_tensor([0.99], dtype="float32")

adam = paddle.optimizer.Adam(learning_rate=0.1,
parameters=linear.parameters(),
beta1=beta1,
beta2=beta2,
weight_decay=0.01)
loss.backward()
adam.step()
adam.clear_grad()

#Note that the learning_rate of linear_2 is 0.01.
linear_1 = paddle.nn.Linear(10, 10)
linear_2 = paddle.nn.Linear(10, 10)
inp = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
out = linear_1(inp)
out = linear_2(out)
loss = paddle.mean(out)
adam = paddle.optimizer.Adam(
learning_rate=0.1,
parameters=[{
'params': linear_1.parameters()
}, {
'params': linear_2.parameters(),
'weight_decay': 0.001,
'learning_rate': 0.1,
'beta1': 0.8
}],
weight_decay=0.01,
beta1=0.9)
loss.backward()
adam.step()
adam.clear_grad()
>>> # Adam with beta1/beta2 as Tensor and weight_decay as float
>>> import paddle
>>> paddle.seed(2023)

>>> linear = paddle.nn.Linear(10, 10)
>>> inp = paddle.rand([10,10], dtype="float32")
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> beta1 = paddle.to_tensor([0.9], dtype="float32")
>>> beta2 = paddle.to_tensor([0.99], dtype="float32")
>>> adam = paddle.optimizer.Adam(learning_rate=0.1,
... parameters=linear.parameters(),
... beta1=beta1,
... beta2=beta2,
... weight_decay=0.01)
>>> loss.backward()
>>> adam.step()
>>> adam.clear_grad()
>>> # Note that the learning_rate of linear_2 is 0.01.
PommesPeter marked this conversation as resolved.
Show resolved Hide resolved
>>> linear_1 = paddle.nn.Linear(10, 10)
>>> linear_2 = paddle.nn.Linear(10, 10)
>>> inp = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
>>> out = linear_1(inp)
>>> out = linear_2(out)
>>> loss = paddle.mean(out)
>>> adam = paddle.optimizer.Adam(
... learning_rate=0.1,
... parameters=[{
... 'params': linear_1.parameters()
... }, {
... 'params': linear_2.parameters(),
... 'weight_decay': 0.001,
... 'learning_rate': 0.1,
... 'beta1': 0.8
... }],
... weight_decay=0.01,
... beta1=0.9)
>>> loss.backward()
>>> adam.step()
>>> adam.clear_grad()

"""
_moment1_acc_str = "moment1"
Expand Down Expand Up @@ -409,17 +408,17 @@ def step(self):
Examples:
.. code-block:: python

import paddle

a = paddle.rand([2,13], dtype="float32")
linear = paddle.nn.Linear(13, 5)
# This can be any optimizer supported by dygraph.
adam = paddle.optimizer.Adam(learning_rate = 0.01,
parameters = linear.parameters())
out = linear(a)
out.backward()
adam.step()
adam.clear_grad()
>>> import paddle

>>> a = paddle.rand([2,13], dtype="float32")
>>> linear = paddle.nn.Linear(13, 5)
>>> # This can be any optimizer supported by dygraph.
>>> adam = paddle.optimizer.Adam(learning_rate = 0.01,
... parameters = linear.parameters())
>>> out = linear(a)
>>> out.backward()
>>> adam.step()
>>> adam.clear_grad()
"""
if paddle.fluid.dygraph.base.in_declarative_mode():
self._declarative_step()
Expand Down