singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "zhangzhaoqi (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (SINGA-476) Autograd operators for ONNX
Date Wed, 31 Jul 2019 04:05:00 GMT

     [ https://issues.apache.org/jira/browse/SINGA-476?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

zhangzhaoqi updated SINGA-476:
------------------------------
    Description: 
For the demo purpose, we need to implement these three models, and these are their components:
h2. Tiny yolov2[link title|https://arxiv.org/pdf/1612.08242.pdf]

MaxPooling2D
 Conv2D
 BatchNormalization
 LeakyReLU
 Reshape
h2. Arcface[link title|https://arxiv.org/abs/1801.07698]

Conv2D
 BatchNormalization
 relu
 MaxPooling2D
 Dropout
 Flatten
 Dense
 Softmax
 l2_normalize
 acos
 cos
h2. BIDAF[link title|https://arxiv.org/pdf/1611.01603]

K.stack
 Softmax
 K.expand_dims
 K.sum
 Constant
 Dense
 Lambda(lambda x: 1.0 - x, output_shape=(dim,))
 Multiply
 Add
 K.concatenate
 K.shape
 K.max
 K.tile
 K.squeeze
 linear
 TimeDistributed
 Bidirectional(LSTM

 

 

In summary, we already implemented 12 ops, and there still are 16 ops needed to be implemented:
h2. Already implemented:

-LSTM-
 -Multiply-
 -Add-
 -linear-
 -relu-
 -acos-
 -cos-
 -LeakyReLU-
 -Softmax-
 -MaxPooling2D-
 -Conv2D-
 -BatchNormalization-
h2.  To be implemented:

Reshape
 Flatten
 Dropout
 max
 shape
 concatenate
 Constant
 L2Normalization
 Expand
 tile
 squeeze
 Dense*
 TimeDistributed*
 Bidirectional*
 Stack*
 Lambda*

*means this op doesn't have a corresponding one at ONNX op sets, therefore, it needs a converter
function by using basic op sets.

 

  was:
For the demo purpose, we need to implement these three models, and these are their components:
h2. Tiny yolov2[link title|https://arxiv.org/pdf/1612.08242.pdf]

MaxPooling2D
Conv2D
BatchNormalization
LeakyReLU
Reshape
h2. Arcface[link title|https://arxiv.org/abs/1801.07698]

Conv2D
BatchNormalization
relu
MaxPooling2D
Dropout
Flatten
Dense
Softmax
l2_normalize
acos
cos
h2. BIDAF[link title|https://arxiv.org/pdf/1611.01603]

K.stack
Softmax
K.expand_dims
K.sum
Constant
Dense
Lambda(lambda x: 1.0 - x, output_shape=(dim,))
Multiply
Add
K.concatenate
K.shape
K.max
K.tile
K.squeeze
linear
TimeDistributed
Bidirectional(LSTM
h2. In summary, 
h2. Already implemented:

-LSTM-
 -Multiply-
 -Add-
 -linear-
 -relu-
 -acos-
 -cos-
 -LeakyReLU-
 -Softmax-
 -MaxPooling2D-
 -Conv2D-
 -BatchNormalization-
h2.  To be implemented:

Reshape
 Flatten
 Dropout
 max
 shape
 concatenate
 Constant
 L2Normalization
 Expand
 tile
 squeeze
 Dense*
 TimeDistributed*
 Bidirectional*
 Stack*
 Lambda*

*means this op doesn't have a corresponding one at ONNX op sets, therefore, it needs a converter
function by using basic op sets.

 


> Autograd operators for ONNX
> ---------------------------
>
>                 Key: SINGA-476
>                 URL: https://issues.apache.org/jira/browse/SINGA-476
>             Project: Singa
>          Issue Type: New Feature
>            Reporter: zhangzhaoqi
>            Priority: Critical
>
> For the demo purpose, we need to implement these three models, and these are their components:
> h2. Tiny yolov2[link title|https://arxiv.org/pdf/1612.08242.pdf]
> MaxPooling2D
>  Conv2D
>  BatchNormalization
>  LeakyReLU
>  Reshape
> h2. Arcface[link title|https://arxiv.org/abs/1801.07698]
> Conv2D
>  BatchNormalization
>  relu
>  MaxPooling2D
>  Dropout
>  Flatten
>  Dense
>  Softmax
>  l2_normalize
>  acos
>  cos
> h2. BIDAF[link title|https://arxiv.org/pdf/1611.01603]
> K.stack
>  Softmax
>  K.expand_dims
>  K.sum
>  Constant
>  Dense
>  Lambda(lambda x: 1.0 - x, output_shape=(dim,))
>  Multiply
>  Add
>  K.concatenate
>  K.shape
>  K.max
>  K.tile
>  K.squeeze
>  linear
>  TimeDistributed
>  Bidirectional(LSTM
>  
>  
> In summary, we already implemented 12 ops, and there still are 16 ops needed to be implemented:
> h2. Already implemented:
> -LSTM-
>  -Multiply-
>  -Add-
>  -linear-
>  -relu-
>  -acos-
>  -cos-
>  -LeakyReLU-
>  -Softmax-
>  -MaxPooling2D-
>  -Conv2D-
>  -BatchNormalization-
> h2.  To be implemented:
> Reshape
>  Flatten
>  Dropout
>  max
>  shape
>  concatenate
>  Constant
>  L2Normalization
>  Expand
>  tile
>  squeeze
>  Dense*
>  TimeDistributed*
>  Bidirectional*
>  Stack*
>  Lambda*
> *means this op doesn't have a corresponding one at ONNX op sets, therefore, it needs
a converter function by using basic op sets.
>  



--
This message was sent by Atlassian JIRA
(v7.6.14#76016)

Mime
View raw message