mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-06-26 03:00:54 +00:00
fix some typo in docs (#13212)
### Description <!-- Describe your changes. --> fix some typo in docs ### Motivation and Context singed vs signed succeding vs succeeding fileter vs filter kernal vs kernel libary vs library
This commit is contained in:
garanews
GitHub
parent
d411bd277e
commit
38906625a3
7 changed files with 12 additions and 12 deletions
|
|
@ -1839,7 +1839,7 @@ This version of the operator has been available since version 1 of the 'com.micr
|
|||
### <a name="com.microsoft.LongformerAttention"></a><a name="com.microsoft.longformerattention">**com.microsoft.LongformerAttention**</a>
|
||||
|
||||
Longformer Self Attention with a local context and a global context. Tokens attend locally: Each token
|
||||
attends to its W previous tokens and W succeding tokens with W being the window length. A selected few tokens
|
||||
attends to its W previous tokens and W succeeding tokens with W being the window length. A selected few tokens
|
||||
attend globally to all other tokens.
|
||||
|
||||
The attention mask is of shape (batch_size, sequence_length), where sequence_length is a multiple of 2W after padding.
|
||||
|
|
@ -2723,7 +2723,7 @@ This version of the operator has been available since version 1 of the 'com.micr
|
|||
|
||||
<dl>
|
||||
<dt><tt>T</tt> : tensor(uint8), tensor(int8)</dt>
|
||||
<dd>Constrain input and output types to singed/unsigned int8 tensors.</dd>
|
||||
<dd>Constrain input and output types to signed/unsigned int8 tensors.</dd>
|
||||
</dl>
|
||||
|
||||
|
||||
|
|
@ -2965,7 +2965,7 @@ This version of the operator has been available since version 1 of the 'com.micr
|
|||
|
||||
<dl>
|
||||
<dt><tt>T</tt> : tensor(uint8), tensor(int8)</dt>
|
||||
<dd>Constrain input and output types to singed/unsigned int8 tensors.</dd>
|
||||
<dd>Constrain input and output types to signed/unsigned int8 tensors.</dd>
|
||||
</dl>
|
||||
|
||||
|
||||
|
|
@ -4002,9 +4002,9 @@ This version of the operator has been available since version 1 of the 'com.micr
|
|||
<dt><tt>char_embedding_size</tt> : int</dt>
|
||||
<dd>Integer representing the embedding vector size for each char.If not provide, use the char embedding size of embedding vector.</dd>
|
||||
<dt><tt>conv_window_size</tt> : int</dt>
|
||||
<dd>This operator applies convolution to word from left to right with window equal to conv_window_size and stride to 1.Take word 'example' for example, with conv_window_size equal to 2, conv is applied to [ex],[xa], [am], [mp]...If not provide, use the first dimension of conv kernal shape.</dd>
|
||||
<dd>This operator applies convolution to word from left to right with window equal to conv_window_size and stride to 1.Take word 'example' for example, with conv_window_size equal to 2, conv is applied to [ex],[xa], [am], [mp]...If not provide, use the first dimension of conv kernel shape.</dd>
|
||||
<dt><tt>embedding_size</tt> : int</dt>
|
||||
<dd>Integer representing the embedding vector size for each word.If not provide, use the fileter size of conv weight</dd>
|
||||
<dd>Integer representing the embedding vector size for each word.If not provide, use the filter size of conv weight</dd>
|
||||
</dl>
|
||||
|
||||
#### Inputs
|
||||
|
|
|
|||
|
|
@ -157,7 +157,7 @@ CMAKE_HOST_SYSTEM_PROCESSOR is the one you should use.
|
|||
|
||||
What are the valid values:
|
||||
- macOS: it can be x86_64 or arm64. (maybe it could also be arm64e but cmake forgot to document that)
|
||||
- Linux: i686, x86_64, aarch64, armv7l, ... The possible values for `uname -m` command. They sightly differ from what you can get from GCC. This sometimes confuses people: `cmake` and `uname` sit in one boat, GCC is in another boat but GCC is closer to your C/C++ source code.
|
||||
- Linux: i686, x86_64, aarch64, armv7l, ... The possible values for `uname -m` command. They slightly differ from what you can get from GCC. This sometimes confuses people: `cmake` and `uname` sit in one boat, GCC is in another boat but GCC is closer to your C/C++ source code.
|
||||
- Windows: AMD64, ...
|
||||
- Android/iOS/...: we don't care. We don't use them as a development environment.
|
||||
|
||||
|
|
|
|||
|
|
@ -265,7 +265,7 @@ Internal classes
|
|||
----------------
|
||||
|
||||
These classes cannot be instantiated by users but they are returned
|
||||
by methods or functions of this libary.
|
||||
by methods or functions of this library.
|
||||
|
||||
ModelMetadata
|
||||
^^^^^^^^^^^^^
|
||||
|
|
|
|||
|
|
@ -100,7 +100,7 @@ ONNX_MS_OPERATOR_SET_SCHEMA(Attention, 1,
|
|||
|
||||
constexpr const char* Longformer_Attention_doc = R"DOC(
|
||||
Longformer Self Attention with a local context and a global context. Tokens attend locally: Each token
|
||||
attends to its W previous tokens and W succeding tokens with W being the window length. A selected few tokens
|
||||
attends to its W previous tokens and W succeeding tokens with W being the window length. A selected few tokens
|
||||
attend globally to all other tokens.
|
||||
|
||||
The attention mask is of shape (batch_size, sequence_length), where sequence_length is a multiple of 2W after padding.
|
||||
|
|
|
|||
|
|
@ -1756,14 +1756,14 @@ ONNX_MS_OPERATOR_SET_SCHEMA(WordConvEmbedding, 1,
|
|||
.Attr(
|
||||
"embedding_size",
|
||||
"Integer representing the embedding vector size for each word."
|
||||
"If not provide, use the fileter size of conv weight",
|
||||
"If not provide, use the filter size of conv weight",
|
||||
AttributeProto::INT,
|
||||
OPTIONAL_VALUE)
|
||||
.Attr(
|
||||
"conv_window_size",
|
||||
"This operator applies convolution to word from left to right with window equal to conv_window_size and stride to 1."
|
||||
"Take word 'example' for example, with conv_window_size equal to 2, conv is applied to [ex],[xa], [am], [mp]..."
|
||||
"If not provide, use the first dimension of conv kernal shape.",
|
||||
"If not provide, use the first dimension of conv kernel shape.",
|
||||
AttributeProto::INT,
|
||||
OPTIONAL_VALUE)
|
||||
.Attr(
|
||||
|
|
|
|||
|
|
@ -71,7 +71,7 @@ equal to the spatial dimension of input tensor. Input is of type uint8_t or int8
|
|||
"dimensions are all 1.",
|
||||
"T")
|
||||
.TypeConstraint("T", {"tensor(uint8)", "tensor(int8)"},
|
||||
"Constrain input and output types to singed/unsigned int8 tensors.")
|
||||
"Constrain input and output types to signed/unsigned int8 tensors.")
|
||||
.TypeAndShapeInferenceFunction([](ONNX_NAMESPACE::InferenceContext& ctx) {
|
||||
propagateElemTypeFromInputToOutput(ctx, 0, 0);
|
||||
|
||||
|
|
|
|||
|
|
@ -617,7 +617,7 @@ The output tensor has the same shape.
|
|||
"tensor. The output tensor has the same rank as the input. ",
|
||||
"T")
|
||||
.TypeConstraint("T", {"tensor(uint8)", "tensor(int8)"},
|
||||
"Constrain input and output types to singed/unsigned int8 tensors.")
|
||||
"Constrain input and output types to signed/unsigned int8 tensors.")
|
||||
.TypeAndShapeInferenceFunction([](ONNX_NAMESPACE::InferenceContext& ctx) {
|
||||
// Type inference
|
||||
propagateElemTypeFromInputToOutput(ctx, 0, 0);
|
||||
|
|
|
|||
Loading…
Reference in a new issue