Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
28 commits
Select commit Hold shift + click to select a range
ae63b81
修复tensorflow的链接失效问题,对应表格第一列
Echo-Nie Oct 7, 2025
bc6135b
Merge branch 'TensorFlow-Paddle-docs' of https://github.com/Echo-Nie/…
Echo-Nie Oct 28, 2025
0b70372
Fix typo in TensorFlow initializer link
Echo-Nie Oct 29, 2025
c98c29f
Fix links to PaddlePaddle API in tensor_cn.md
Echo-Nie Oct 29, 2025
f04452e
Update image links in tensor_cn.md
Echo-Nie Oct 29, 2025
885c628
Update image links in tensor_en.md
Echo-Nie Oct 29, 2025
005cb12
Update image URLs to include raw parameter
Echo-Nie Oct 29, 2025
68c7ee4
Fix ROCm documentation links and file paths
Echo-Nie Oct 29, 2025
77d39ca
Update links in tensor_cn.md to point to new URLs
Echo-Nie Oct 29, 2025
b60b413
Update links in tensor_cn.md to relative paths
Echo-Nie Oct 29, 2025
c64cf95
Merge branch 'PaddlePaddle:develop' into TensorFlow-Paddle-docs
Echo-Nie Oct 30, 2025
91855e1
Delete docs/api_guides/X2Paddle/TensorFlow-Fluid.rst
Echo-Nie Oct 30, 2025
9169f40
Delete docs/api_guides/X2Paddle/Caffe-Fluid.rst
Echo-Nie Oct 30, 2025
8fd0356
Fix C++ Data Feeding link in Python Data Feeding doc
Echo-Nie Oct 30, 2025
a4f3f38
Update image links in channel documentation
Echo-Nie Oct 30, 2025
9b41f77
Change image source in select_op documentation
Echo-Nie Oct 30, 2025
98373d2
Fix C++ Data Feeding link in Python Data Feeding doc
Echo-Nie Oct 30, 2025
c005498
Update reference format for SubmConv2D_cn.rst
Echo-Nie Oct 30, 2025
a37d160
Update PSROIPooling reference in documentation
Echo-Nie Oct 30, 2025
ec4e713
Update FastEmit parameter description in RNNTLoss_cn.rst
Echo-Nie Oct 30, 2025
83ad364
Update reference format in hardswish_cn.rst
Echo-Nie Oct 30, 2025
7ea9c73
Update label smoothing reference in documentation
Echo-Nie Oct 30, 2025
cd5c193
Update fastemit_lambda description with reference link
Echo-Nie Oct 30, 2025
a536830
Merge branch 'PaddlePaddle:develop' into TensorFlow-Paddle-docs
Echo-Nie Nov 1, 2025
e61f2fa
fix png links
Echo-Nie Nov 1, 2025
32f7542
fix according to the review
Echo-Nie Nov 1, 2025
c4541bc
Fix links for MIOpen operator registration
Echo-Nie Nov 2, 2025
2af003b
Merge branch 'develop' into TensorFlow-Paddle-docs
Echo-Nie Nov 3, 2025
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
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/RNNTLoss_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ RNNTLoss
参数
:::::::::
- **blank** (int,可选) - 空格标记的 ID 值,其取值范围为 [0, num_classes + 1)。数据类型支持 int32。默认值为 0。
- **fastemit_lambda** (float,默认 0.001) - FastEmit 的正则化参数(https://arxiv.org/pdf/2010.11148.pdf)
- **fastemit_lambda** (float,默认 0.001) - FastEmit 的正则化参数,具体请参考:`FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization <https://arxiv.org/pdf/2010.11148.pdf>`_
- **reduction** (str,可选) - 表示如何平均损失,候选是 ``'none'`` | ``'mean'`` | ``'sum'`` 。如果是 ``'mean'`` ,输出将是损失的总和并除以 batch_size;如果是 ``'sum'``,返回损失的总和;如果为 ``'none'``,则不应用 reduction。默认是 ``'mean'``。
- **name** (str,可选) - 操作名称,默认为 None。

Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/functional/hardswish_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ hardswish

.. py:function:: paddle.nn.functional.hardswish(x, name=None)

hardswish 激活函数。在 MobileNetV3 架构中被提出,相较于 swish 函数,具有数值稳定性好,计算速度快等优点,具体原理请参考:https://arxiv.org/pdf/1905.02244.pdf
hardswish 激活函数。在 MobileNetV3 架构中被提出,相较于 swish 函数,具有数值稳定性好,计算速度快等优点,具体原理请参考:`Searching for MobileNetV3 <https://arxiv.org/pdf/1905.02244.pdf>`_ 。

.. math::

Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/functional/label_smooth_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ label_smooth
其中 :math:`1-\epsilon` 和 :math:`\epsilon` 分别是权重,:math:`\tilde{y_k}` 是平滑后的标签,通常 :math:`\mu` 使用均匀分布。


关于更多标签平滑的细节,`查看论文 <https://arxiv.org/abs/1512.00567>`_ 。
关于更多标签平滑的细节请参考论文:`Rethinking the Inception Architecture for Computer Vision <https://arxiv.org/abs/1512.00567>`_ 。


参数
Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/functional/rnnt_loss_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ rnnt_loss
- **input_lengths** (Tensor) - 每个输入序列的长度,它应该有形状 [batch_size] 和 dtype int64。
- **label_lengths** (Tensor) - 每个标签序列的长度,它应该有形状 [batch_size] 和 dtype int64。
- **blank** (int,可选) - RNN-T loss 的空白标签索引,处于半开放区间 [0,B)。数据类型必须为 int32。默认值为 0。
- **fastemit_lambda** (float,默认 0.001) - FastEmit 的正则化参数(https://arxiv.org/pdf/2010.11148.pdf)
- **fastemit_lambda** (float,默认 0.001) - FastEmit 的正则化参数,参考论文:`FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization <https://arxiv.org/pdf/2010.11148.pdf>`_
- **reduction** (str,可选) - 表示如何平均损失,候选是 ``'none'`` | ``'mean'`` | ``'sum'`` 。如果 :attr:`reduction` 是 ``'mean'``,输出将是损失的总和并除以 batch_size;如果 :attr:`reduction` 是 ``'sum'``,返回损失的总和;如果 :attr:`reduction` 为 ``'none'``,则不应用 reduction。默认是 ``'mean'``。
- **name** (str,可选) - 操作名称,默认为 None。

Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/sparse/nn/SubmConv2D_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ SubmConv2D

- :math:`X` : 输入值, NDHWC 格式的 Tencer。
- :math:`W` : 卷积核值, NDHWC 格式的 Tencer。
- :math:`\\ast` : 子流形卷积运算, 参考论文: https://arxiv.org/abs/1706.01307。
- :math:`\\ast` : 子流形卷积运算, 参考论文: `Submanifold Sparse Convolutional Networks <https://arxiv.org/abs/1706.01307>`_
- :math:`b` : 偏置值, 形状为[M]的 1-D Tencer。
- :math:`Out` : 输出值, :math:`Out` 和 :math:`X` 的形状可能不同。

Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/vision/ops/psroi_pool_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ psroi_pool

位置敏感的兴趣区域池化(也称为 PSROIPooling),是在指定输入的感兴趣区域上执行位置敏感的平均池化。它在非均匀大小的输入上执行并获得固定大小的特征图。

PSROIPooling 由 R-FCN 提出。更多详细信息,请参阅 https://arxiv.org/abs/1605.06409。
PSROIPooling 由 R-FCN 提出。更多详细信息,请参阅 `R-FCN: Object Detection via Region-based Fully Convolutional Networks <https://arxiv.org/abs/1605.06409>`_

参数
:::::::::
Expand Down
45 changes: 0 additions & 45 deletions docs/api_guides/X2Paddle/Caffe-Fluid.rst

This file was deleted.

Loading