Merge pull request #29 from dcslin/broadcast-mult-add-example
added broadcast mult, math ops, and added rnn examples
diff --git a/docs-site/docs/onnx.md b/docs-site/docs/onnx.md
index a79a19b..fa4bd65 100644
--- a/docs-site/docs/onnx.md
+++ b/docs-site/docs/onnx.md
@@ -551,11 +551,12 @@
objects in the images into 1000 object categories such as keyboard, mouse,
pencil, and many animals.
-| Model Class | Reference | Description | Link |
-| ---------------------------------------------------------------------------------------------- | -------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| <b>[MobileNet](https://github.com/onnx/models/tree/master/vision/classification/mobilenet)</b> | [Sandler et al.](https://arxiv.org/abs/1801.04381) | Light-weight deep neural network best suited for mobile and embedded vision applications. <br>Top-5 error from paper - ~10% | [](https://colab.research.google.com/drive/1HsixqJMIpKyEPhkbB8jy7NwNEFEAUWAf) |
-| <b>[ResNet18](https://github.com/onnx/models/tree/master/vision/classification/resnet)</b> | [He et al.](https://arxiv.org/abs/1512.03385) | A CNN model (up to 152 layers). Uses shortcut connections to achieve higher accuracy when classifying images. <br> Top-5 error from paper - ~3.6% | [](https://colab.research.google.com/drive/1u1RYefSsVbiP4I-5wiBKHjsT9L0FxLm9) |
-| <b>[VGG16](https://github.com/onnx/models/tree/master/vision/classification/vgg)</b> | [Simonyan et al.](https://arxiv.org/abs/1409.1556) | Deep CNN model(up to 19 layers). Similar to AlexNet but uses multiple smaller kernel-sized filters that provides more accuracy when classifying images. <br>Top-5 error from paper - ~8% | [](https://colab.research.google.com/drive/14kxgRKtbjPCKKsDJVNi3AvTev81Gp_Ds) |
+| Model Class | Reference | Description | Link |
+| --------------------------------------------------------------------------------------------------- | ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| <b>[MobileNet](https://github.com/onnx/models/tree/master/vision/classification/mobilenet)</b> | [Sandler et al.](https://arxiv.org/abs/1801.04381) | Light-weight deep neural network best suited for mobile and embedded vision applications. <br>Top-5 error from paper - ~10% | [](https://colab.research.google.com/drive/1HsixqJMIpKyEPhkbB8jy7NwNEFEAUWAf) |
+| <b>[ResNet18](https://github.com/onnx/models/tree/master/vision/classification/resnet)</b> | [He et al.](https://arxiv.org/abs/1512.03385) | A CNN model (up to 152 layers). Uses shortcut connections to achieve higher accuracy when classifying images. <br> Top-5 error from paper - ~3.6% | [](https://colab.research.google.com/drive/1u1RYefSsVbiP4I-5wiBKHjsT9L0FxLm9) |
+| <b>[VGG16](https://github.com/onnx/models/tree/master/vision/classification/vgg)</b> | [Simonyan et al.](https://arxiv.org/abs/1409.1556) | Deep CNN model(up to 19 layers). Similar to AlexNet but uses multiple smaller kernel-sized filters that provides more accuracy when classifying images. <br>Top-5 error from paper - ~8% | [](https://colab.research.google.com/drive/14kxgRKtbjPCKKsDJVNi3AvTev81Gp_Ds) |
+| <b>[ShuffleNet_V2](https://github.com/onnx/models/tree/master/vision/classification/shufflenet)</b> | [Simonyan et al.](https://arxiv.org/pdf/1707.01083.pdf) | Extremely computation efficient CNN model that is designed specifically for mobile devices. This network architecture design considers direct metric such as speed, instead of indirect metric like FLOP. Top-1 error from paper - ~30.6% | [ |
### Object Detection
@@ -581,89 +582,93 @@
This subset of natural language processing models that answer questions about a
given context paragraph.
-| Model Class | Reference | Description | Link |
-| ----------------------------------------------------------------------------------------------------- | ----------------------------------------------------- | ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| <b>[BERT-Squad](https://github.com/onnx/models/tree/master/text/machine_comprehension/bert-squad)</b> | [Devlin et al.](https://arxiv.org/pdf/1810.04805.pdf) | This model answers questions based on the context of the given input paragraph. | [](https://colab.research.google.com/drive/1kud-lUPjS_u-TkDAzihBTw0Vqr0FjCE-) |
+| Model Class | Reference | Description | Link |
+| ----------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| <b>[BERT-Squad](https://github.com/onnx/models/tree/master/text/machine_comprehension/bert-squad)</b> | [Devlin et al.](https://arxiv.org/pdf/1810.04805.pdf) | This model answers questions based on the context of the given input paragraph. | [](https://colab.research.google.com/drive/1kud-lUPjS_u-TkDAzihBTw0Vqr0FjCE-) |
+| <b>[RoBERTa](https://github.com/onnx/models/tree/master/text/machine_comprehension/roberta)</b> | [Devlin et al.](https://arxiv.org/pdf/1907.11692.pdf) | A large transformer-based model that predicts sentiment based on given input text. | [](https://colab.research.google.com/drive/1F-c4LJSx3Cb2jW6tP7f8nAZDigyLH6iN?usp=sharing) |
+| <b>[GPT-2](https://github.com/onnx/models/tree/master/text/machine_comprehension/gpt-2)</b> | [Devlin et al.](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) | A large transformer-based language model that given a sequence of words within some text, predicts the next word. | [ |
## Supported operators
The following operators are supported:
-- Conv
-- Relu
-- Constant
-- MaxPool
-- AveragePool
-- Softmax
-- Sigmoid
-- Add
-- MatMul
-- BatchNormalization
-- Concat
-- Flatten
-- Add
-- Gemm
-- Reshape
-- Sum
-- Cos
-- Cosh
-- Sin
-- Sinh
-- Tan
-- Tanh
- Acos
- Acosh
+- Add
+- And
- Asin
- Asinh
- Atan
- Atanh
-- Selu
+- AveragePool
+- BatchNormalization
+- Cast
+- Ceil
+- Clip
+- Concat
+- ConstantOfShape
+- Conv
+- Cos
+- Cosh
+- Div
+- Dropout
- Elu
- Equal
-- Less
-- Sign
-- Div
-- Sub
-- Sqrt
-- Log
+- Erf
+- Expand
+- Flatten
+- Gather
+- Gemm
+- GlobalAveragePool
- Greater
- HardSigmoid
- Identity
+- LeakyRelu
+- Less
+- Log
+- MatMul
+- Max
+- MaxPool
+- Mean
+- Min
+- Mul
+- Neg
+- NonZero
+- Not
+- OneHot
+- Or
+- Pad
+- Pow
+- PRelu
+- Reciprocal
+- ReduceMean
+- ReduceSum
+- Relu
+- Reshape
+- ScatterElements
+- Selu
+- Shape
+- Sigmoid
+- Sign
+- Sin
+- Sinh
+- Slice
+- Softmax
- Softplus
- Softsign
-- Mean
-- Pow
-- Clip
-- PRelu
-- Mul
-- Transpose
-- Max
-- Min
-- Shape
-- And
-- Or
-- Xor
-- Not
-- Neg
-- Reciprocal
-- LeakyRelu
-- GlobalAveragePool
-- ConstantOfShape
-- Dropout
-- ReduceSum
-- ReduceMean
-- LeakyRelu
-- GlobalAveragePool
-- Squeeze
-- Unsqueeze
-- Slice
-- Ceil
- Split
-- Gather
+- Sqrt
+- Squeeze
+- Sub
+- Sum
+- Tan
+- Tanh
- Tile
-- NonZero
-- Cast
-- OneHot
+- Transpose
+- Unsqueeze
+- Upsample
+- Where
+- Xor
### Special comments for ONNX backend
