SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add ONNX configuration classes to docs (#15121)

Browse Source 
* Add ONNX classes to main package

* Remove permalinks from ONNX guide

* Fix ToC entry

* Revert "Add ONNX classes to main package"

This reverts commit eb794a5b00d66b0b4eab234987301676d8357630.

* Add ONNX classes to main doc

* Fix syntax highlighting in doc

* Fix text

* Add FeaturesManager to doc

* Use paths to reference ONNX classes

* Add FeaturesManager to init

* Add missing ONNX paths
This commit is contained in:
lewtun
2022-01-12 16:33:32 +01:00
committed by GitHub
parent c425d60bb9
commit 021f2ea987
5 changed files with 67 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
docs/source/serialization.mdx
View File

@@ -109,7 +109,7 @@ which should show the following logs:
```bash
Validating ONNX model...
-[✓] ONNX model outputs' name match reference model ({'last_hidden_state'})
-[✓] ONNX model output names match reference model ({'last_hidden_state'})
- Validating ONNX Model output "last_hidden_state":
-[✓] (2, 8, 768) matches (2, 8, 768)
-[✓] all values close (atol: 1e-05)
@@ -189,7 +189,7 @@ which will display the following logs:
```bash
Validating ONNX model...
-[✓] ONNX model outputs' name match reference model ({'logits'})
-[✓] ONNX model output names match reference model ({'logits'})
- Validating ONNX Model output "logits":
-[✓] (2, 2) matches (2, 2)
-[✓] all values close (atol: 1e-05)
@@ -228,9 +228,9 @@ Let's start with the ONNX configuration object. We provide three abstract
classes that you should inherit from, depending on the type of model
architecture you wish to export:
* Encoder-based models inherit from [`OnnxConfig`](https://github.com/huggingface/transformers/blob/c4fa908fa98c3d538462c537d29b7613dd71306e/src/transformers/onnx/config.py#L52)
* Decoder-based models inherit from [`OnnxConfigWithPast`](https://github.com/huggingface/transformers/blob/c4fa908fa98c3d538462c537d29b7613dd71306e/src/transformers/onnx/config.py#L264)
* Encoder-decoder models inherit from [`OnnxSeq2SeqConfigWithPast`](https://github.com/huggingface/transformers/blob/c4fa908fa98c3d538462c537d29b7613dd71306e/src/transformers/onnx/config.py#L399)
* Encoder-based models inherit from [`~onnx.config.OnnxConfig`]
* Decoder-based models inherit from [`~onnx.config.OnnxConfigWithPast`]
* Encoder-decoder models inherit from [`~onnx.config.OnnxSeq2SeqConfigWithPast`]
<Tip>
@@ -321,11 +321,9 @@ OrderedDict([('logits', {0: 'batch'})])
<Tip>
All of the base properties and methods associated with
[`OnnxConfig`]
and the other configuration classes can be overriden if needed. Check out
[`BartOnnxConfig`]
for an advanced example.
All of the base properties and methods associated with [`~onnx.config.OnnxConfig`] and the
other configuration classes can be overriden if needed. Check out
[`BartOnnxConfig`] for an advanced example.
</Tip>
@@ -400,10 +398,8 @@ to the library, you will need to:
* Implement the ONNX configuration in the corresponding `configuration_<model_name>.py`
file
* Include the model architecture and corresponding features in
[`onnx.features.FeatureManager`](https://github.com/huggingface/transformers/blob/c4fa908fa98c3d538462c537d29b7613dd71306e/src/transformers/onnx/features.py#L71)
* Add your model architecture to the tests in
`test_onnx_v2.py`
* Include the model architecture and corresponding features in [`~onnx.features.FeatureManager`]
* Add your model architecture to the tests in `test_onnx_v2.py`
Check out how the configuration for [IBERT was
contributed](https://github.com/huggingface/transformers/pull/14868/files) to