[jira] [Updated] (SINGA-494) Singa autograd improvement
[ https://issues.apache.org/jira/browse/SINGA-494?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangzhaoqi updated SINGA-494: -- Description: Background: some autograd ops cannot satisfy the onnx demand, as following: # *conv, averagepool, maxpool* - only support 2d input, i.e, N*C*W*H - not support SAME_UPPER, SAME_LOWER, count_include_pad and ceil_mod # *reshape* - not support zero_dim, zero_and_negative_dim # *concat* - not support 1d # *matmul* - only support 2d # *min, max* - only support 2 inputs # *add* - not support broadcast # *and, or, xor* - not support broadcast # *div, pow, prelu* - not support broadcast Some improvements are being done. was: Background: some autograd ops cannot satisfy the onnx demand, as following: # conv, averagepool, maxpool - only support 2d input, i.e, N*C*W*H - not support SAME_UPPER, SAME_LOWER, count_include_pad and ceil_mode # reshape - not support zero_dim, zero_and_negative_dim # concat - not support 1d # matmul - only support 2d # min, max - only support 2 inputs # add - not support broadcast # and, or, xor - not support broadcast # div, pow, prelu - not support broadcast Some improvements are being done. > Singa autograd improvement > -- > > Key: SINGA-494 > URL: https://issues.apache.org/jira/browse/SINGA-494 > Project: Singa > Issue Type: New Feature >Reporter: zhangzhaoqi >Priority: Major > > Background: some autograd ops cannot satisfy the onnx demand, as following: > # *conv, averagepool, maxpool* > - only support 2d input, i.e, N*C*W*H > - not support SAME_UPPER, SAME_LOWER, count_include_pad and ceil_mod > # *reshape* > - not support zero_dim, zero_and_negative_dim > # *concat* > - not support 1d > # *matmul* > - only support 2d > # *min, max* > - only support 2 inputs > # *add* > - not support broadcast > # *and, or, xor* > - not support broadcast > # *div, pow, prelu* > - not support broadcast > Some improvements are being done. -- This message was sent by Atlassian Jira (v8.3.4#803005)
[jira] [Created] (SINGA-489) Add onnx backend test cases for the new operators
zhangzhaoqi created SINGA-489: - Summary: Add onnx backend test cases for the new operators Key: SINGA-489 URL: https://issues.apache.org/jira/browse/SINGA-489 Project: Singa Issue Type: New Feature Reporter: zhangzhaoqi Add onnx backend test cases for the new operators at 'SINGA-471' -- This message was sent by Atlassian Jira (v8.3.2#803003)
[jira] [Closed] (SINGA-483) fix dummy bugs
[ https://issues.apache.org/jira/browse/SINGA-483?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangzhaoqi closed SINGA-483. - Resolution: Fixed > fix dummy bugs > -- > > Key: SINGA-483 > URL: https://issues.apache.org/jira/browse/SINGA-483 > Project: Singa > Issue Type: New Feature >Reporter: zhangzhaoqi >Priority: Major > Time Spent: 10m > Remaining Estimate: 0h > > There is a but at autograd dummy operator. It should call __getattribute__ > function to get tensor's attribute, not directly use the name. -- This message was sent by Atlassian Jira (v8.3.2#803003)
[jira] [Updated] (SINGA-481) Reconstruct SONNX
[ https://issues.apache.org/jira/browse/SINGA-481?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangzhaoqi updated SINGA-481: -- Description: * Reconstruct the frontend and backend of soonx, and make it support transfer learning. * Develop soonx operators: conv2d, relu, avg_pool, softmax, sigmoid, add, concat, matmul * Add these operators' test cases. was: * Reconstruct the frontend and backend of soonx, and make it support transfer learning. * Develop soonx operators: conv2d, relu, avg_pool, softmax, sigmoid, add, concat, matmul * Add these operators' test cases. > Reconstruct SONNX > - > > Key: SINGA-481 > URL: https://issues.apache.org/jira/browse/SINGA-481 > Project: Singa > Issue Type: New Feature >Reporter: zhangzhaoqi >Priority: Major > Time Spent: 1h 20m > Remaining Estimate: 0h > > * Reconstruct the frontend and backend of soonx, and make it support transfer > learning. > * Develop soonx operators: conv2d, relu, avg_pool, softmax, sigmoid, add, > concat, matmul > * Add these operators' test cases. -- This message was sent by Atlassian Jira (v8.3.2#803003)
[jira] [Created] (SINGA-483) fix dummy bugs
zhangzhaoqi created SINGA-483: - Summary: fix dummy bugs Key: SINGA-483 URL: https://issues.apache.org/jira/browse/SINGA-483 Project: Singa Issue Type: New Feature Reporter: zhangzhaoqi There is a but at autograd dummy operator. It should call __getattribute__ function to get tensor's attribute, not directly use the name. -- This message was sent by Atlassian JIRA (v7.6.14#76016)
[jira] [Created] (SINGA-481) Reconstruct SONNX
zhangzhaoqi created SINGA-481: - Summary: Reconstruct SONNX Key: SINGA-481 URL: https://issues.apache.org/jira/browse/SINGA-481 Project: Singa Issue Type: New Feature Reporter: zhangzhaoqi * Reconstruct the frontend and backend of soonx, and make it support transfer learning. * Develop soonx operators: conv2d, relu, avg_pool, softmax, sigmoid, add, concat, matmul * Add these operators' test cases. -- This message was sent by Atlassian JIRA (v7.6.14#76016)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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 their components as following: h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] Add BatchNormalization Conv LeakyRelu MaxPool Mul h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Acos Add BatchNormalization Conv Cos Dropout Flatten Gemm Identity InstanceNormalization LpNormalization Mul PRelu Reshape Sub h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] Abs Add Add ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Conv Dropout Gather Hardmax Log LSTM MatMul ReduceMax ReduceSum Relu Shape Sigmoid Slice Squeeze Sub Sum Transpose Unsqueeze In summary, we already implemented 13 ops, and there're still 27 ops needed to be implemented: h2. Already implemented: -Acos- -BatchNormalization- -Cos- -Conv- -LeakyRelu- -LSTM- -Abs- -MaxPool- -Flatten- -Add- -MatMul- -Relu- -Sigmoid- h2. To be implemented: ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Dropout Gather Gemm Hardmax Identity InstanceNormalization Log LpNormalization Mul PRelu ReduceMax ReduceSum Reshape Shape Slice Squeeze Sub Sum Transpose Unsqueeze Please refer to the [ONNX Operator Schemas| [https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for more detailed information. was: For the demo purpose, we need to implement these three models and their components as following: h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] Add BatchNormalization Conv LeakyRelu MaxPool Mul h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Acos Add BatchNormalization Conv Cos Dropout Flatten Gemm Identity InstanceNormalization LpNormalization Mul PRelu Reshape Sub h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] Abs Add Add ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Conv Dropout Gather Hardmax Log LSTM MatMul ReduceMax ReduceSum Relu Shape Sigmoid Slice Squeeze Sub Sum Transpose Unsqueeze In summary, we already implemented 13 ops, and there're still 27 ops needed to be implemented: h2. Already implemented: -Acos- -BatchNormalization- -Cos- -Conv- -LeakyRelu- -LSTM- -Abs- -MaxPool- -Flatten- -Add- -MatMul- -Relu- -Sigmoid- h2. To be implemented: ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Dropout Gather Gemm Hardmax Identity InstanceNormalization Log LpNormalization Mul PRelu ReduceMax ReduceSum Reshape Shape Slice Squeeze Sub Sum Transpose Unsqueeze Please refer to the [ONNX Operator Schemas|[https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for more detailed information. > 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 > Attachments: arcface(based resnet100).png, bidaf.png, tiny_yolov2.png > > > For the demo purpose, we need to implement these three models and their > components as following: > h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] > Add > BatchNormalization > Conv > LeakyRelu > MaxPool > Mul > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Acos > Add > BatchNormalization > Conv > Cos > Dropout > Flatten > Gemm > Identity > InstanceNormalization > LpNormalization > Mul > PRelu > Reshape > Sub > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > Abs > Add > Add > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Conv > Dropout > Gather > Hardmax > Log > LSTM > MatMul > ReduceMax > ReduceSum > Relu > Shape > Sigmoid > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > > In summary, we already implemented 13 ops, and there're still 27 ops needed > to be implemented: > h2. Already implemented: > -Acos- > -BatchNormalization- > -Cos- > -Conv- > -LeakyRelu- > -LSTM- > -Abs- > -MaxPool- > -Flatten- > -Add- > -MatMul- > -Relu- > -Sigmoid- > h2. To be implemented: > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Dropout > Gather > Gemm > Hardmax > Identity > InstanceNormalization > Log > LpNormalization > Mul > PRelu > ReduceMax > ReduceSum > Reshape > Shape > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > Please refer to the [ONNX Operator Schemas| > [https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for more > detailed information. -- This message was sent by Atlassian JIRA (v7.6.14#76016)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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 their components as following: h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] Add BatchNormalization Conv LeakyRelu MaxPool Mul h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Acos Add BatchNormalization Conv Cos Dropout Flatten Gemm Identity InstanceNormalization LpNormalization Mul PRelu Reshape Sub h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] Abs Add Add ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Conv Dropout Gather Hardmax Log LSTM MatMul ReduceMax ReduceSum Relu Shape Sigmoid Slice Squeeze Sub Sum Transpose Unsqueeze In summary, we already implemented 13 ops, and there're still 27 ops needed to be implemented: h2. Already implemented: -Acos- -BatchNormalization- -Cos- -Conv- -LeakyRelu- -LSTM- -Abs- -MaxPool- -Flatten- -Add- -MatMul- -Relu- -Sigmoid- h2. To be implemented: ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Dropout Gather Gemm Hardmax Identity InstanceNormalization Log LpNormalization Mul PRelu ReduceMax ReduceSum Reshape Shape Slice Squeeze Sub Sum Transpose Unsqueeze Please refer to the [ONNX Operator Schemas| https://github.com/onnx/onnx/blob/master/docs/Operators.md] for more detailed information. was: For the demo purpose, we need to implement these three models and their components as following: h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] Add BatchNormalization Conv LeakyRelu MaxPool Mul h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Acos Add BatchNormalization Conv Cos Dropout Flatten Gemm Identity InstanceNormalization LpNormalization Mul PRelu Reshape Sub h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] Abs Add Add ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Conv Dropout Gather Hardmax Log LSTM MatMul ReduceMax ReduceSum Relu Shape Sigmoid Slice Squeeze Sub Sum Transpose Unsqueeze In summary, we already implemented 13 ops, and there're still 27 ops needed to be implemented: h2. Already implemented: -Acos- -BatchNormalization- -Cos- -Conv- -LeakyRelu- -LSTM- -Abs- -MaxPool- -Flatten- -Add- -MatMul- -Relu- -Sigmoid- h2. To be implemented: ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Dropout Gather Gemm Hardmax Identity InstanceNormalization Log LpNormalization Mul PRelu ReduceMax ReduceSum Reshape Shape Slice Squeeze Sub Sum Transpose Unsqueeze Please refer to the [ONNX Operator Schemas| [https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for more detailed information. > 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 > Attachments: arcface(based resnet100).png, bidaf.png, tiny_yolov2.png > > > For the demo purpose, we need to implement these three models and their > components as following: > h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] > Add > BatchNormalization > Conv > LeakyRelu > MaxPool > Mul > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Acos > Add > BatchNormalization > Conv > Cos > Dropout > Flatten > Gemm > Identity > InstanceNormalization > LpNormalization > Mul > PRelu > Reshape > Sub > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > Abs > Add > Add > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Conv > Dropout > Gather > Hardmax > Log > LSTM > MatMul > ReduceMax > ReduceSum > Relu > Shape > Sigmoid > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > > In summary, we already implemented 13 ops, and there're still 27 ops needed > to be implemented: > h2. Already implemented: > -Acos- > -BatchNormalization- > -Cos- > -Conv- > -LeakyRelu- > -LSTM- > -Abs- > -MaxPool- > -Flatten- > -Add- > -MatMul- > -Relu- > -Sigmoid- > h2. To be implemented: > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Dropout > Gather > Gemm > Hardmax > Identity > InstanceNormalization > Log > LpNormalization > Mul > PRelu > ReduceMax > ReduceSum > Reshape > Shape > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > Please refer to the [ONNX Operator Schemas| > https://github.com/onnx/onnx/blob/master/docs/Operators.md] for more detailed > information. -- This message was sent by Atlassian JIRA (v7.6.14#76016)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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 their components as following: h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] Add BatchNormalization Conv LeakyRelu MaxPool Mul h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Acos Add BatchNormalization Conv Cos Dropout Flatten Gemm Identity InstanceNormalization LpNormalization Mul PRelu Reshape Sub h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] Abs Add Add ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Conv Dropout Gather Hardmax Log LSTM MatMul ReduceMax ReduceSum Relu Shape Sigmoid Slice Squeeze Sub Sum Transpose Unsqueeze In summary, we already implemented 13 ops, and there're still 27 ops needed to be implemented: h2. Already implemented: -Acos- -BatchNormalization- -Cos- -Conv- -LeakyRelu- -LSTM- -Abs- -MaxPool- -Flatten- -Add- -MatMul- -Relu- -Sigmoid- h2. To be implemented: ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Dropout Gather Gemm Hardmax Identity InstanceNormalization Log LpNormalization Mul PRelu ReduceMax ReduceSum Reshape Shape Slice Squeeze Sub Sum Transpose Unsqueeze Please refer to the [ONNX Operator Schemas|[https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for more detailed information. was: For the demo purpose, we need to implement these three models, and these are their components: h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] Add BatchNormalization Conv LeakyRelu MaxPool Mul h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Acos Add BatchNormalization Conv Cos Dropout Flatten Gemm Identity InstanceNormalization LpNormalization Mul PRelu Reshape Sub h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] Abs Add Add ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Conv Dropout Gather Hardmax Log LSTM MatMul ReduceMax ReduceSum Relu Shape Sigmoid Slice Squeeze Sub Sum Transpose Unsqueeze In summary, we already implemented 13 ops, and they're still 27 ops needed to be implemented: h2. Already implemented: -Acos- -BatchNormalization- -Cos- -Conv- -LeakyRelu- -LSTM- -Abs- -MaxPool- -Flatten- -Add- -MatMul- -Relu- -Sigmoid- h2. To be implemented: ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Dropout Gather Gemm Hardmax Identity InstanceNormalization Log LpNormalization Mul PRelu ReduceMax ReduceSum Reshape Shape Slice Squeeze Sub Sum Transpose Unsqueeze Please refer to the [ONNX Operator Schemas|[https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for more detailed information. > 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 > Attachments: arcface(based resnet100).png, bidaf.png, tiny_yolov2.png > > > For the demo purpose, we need to implement these three models and their > components as following: > h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] > Add > BatchNormalization > Conv > LeakyRelu > MaxPool > Mul > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Acos > Add > BatchNormalization > Conv > Cos > Dropout > Flatten > Gemm > Identity > InstanceNormalization > LpNormalization > Mul > PRelu > Reshape > Sub > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > Abs > Add > Add > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Conv > Dropout > Gather > Hardmax > Log > LSTM > MatMul > ReduceMax > ReduceSum > Relu > Shape > Sigmoid > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > > In summary, we already implemented 13 ops, and there're still 27 ops needed > to be implemented: > h2. Already implemented: > -Acos- > -BatchNormalization- > -Cos- > -Conv- > -LeakyRelu- > -LSTM- > -Abs- > -MaxPool- > -Flatten- > -Add- > -MatMul- > -Relu- > -Sigmoid- > h2. To be implemented: > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Dropout > Gather > Gemm > Hardmax > Identity > InstanceNormalization > Log > LpNormalization > Mul > PRelu > ReduceMax > ReduceSum > Reshape > Shape > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > Please refer to the [ONNX Operator > Schemas|[https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for > more detailed information. -- This message was sent by Atlassian JIRA (v7.6.14#76016)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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|https://arxiv.org/pdf/1612.08242.pdf] Add BatchNormalization Conv LeakyRelu MaxPool Mul h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Acos Add BatchNormalization Conv Cos Dropout Flatten Gemm Identity InstanceNormalization LpNormalization Mul PRelu Reshape Sub h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] Abs Add Add ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Conv Dropout Gather Hardmax Log LSTM MatMul ReduceMax ReduceSum Relu Shape Sigmoid Slice Squeeze Sub Sum Transpose Unsqueeze In summary, we already implemented 13 ops, and they're still 27 ops needed to be implemented: h2. Already implemented: -Acos- -BatchNormalization- -Cos- -Conv- -LeakyRelu- -LSTM- -Abs- -MaxPool- -Flatten- -Add- -MatMul- -Relu- -Sigmoid- h2. To be implemented: ArgMax Cast Ceil Clip Compress Concat ConstantOfShape Dropout Gather Gemm Hardmax Identity InstanceNormalization Log LpNormalization Mul PRelu ReduceMax ReduceSum Reshape Shape Slice Squeeze Sub Sum Transpose Unsqueeze Please refer to the [ONNX Operator Schemas|[https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for more detailed information. was: For the demo purpose, we need to implement these three models, and these are their components: h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] MaxPooling2D Conv2D BatchNormalization LeakyReLU Reshape h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Conv2D BatchNormalization relu MaxPooling2D Dropout Flatten Dense Softmax l2_normalize acos cos h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] 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. > 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 > Attachments: arcface(based resnet100).png, bidaf.png, tiny_yolov2.png > > > For the demo purpose, we need to implement these three models, and these are > their components: > h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] > Add > BatchNormalization > Conv > LeakyRelu > MaxPool > Mul > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Acos > Add > BatchNormalization > Conv > Cos > Dropout > Flatten > Gemm > Identity > InstanceNormalization > LpNormalization > Mul > PRelu > Reshape > Sub > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > Abs > Add > Add > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Conv > Dropout > Gather > Hardmax > Log > LSTM > MatMul > ReduceMax > ReduceSum > Relu > Shape > Sigmoid > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > > In summary, we already implemented 13 ops, and they're still 27 ops needed to > be implemented: > h2. Already implemented: > -Acos- > -BatchNormalization- > -Cos- > -Conv- > -LeakyRelu- > -LSTM- > -Abs- > -MaxPool- > -Flatten- > -Add- > -MatMul- > -Relu- > -Sigmoid- > h2. To be implemented: > ArgMax > Cast > Ceil > Clip > Compress > Concat > ConstantOfShape > Dropout > Gather > Gemm > Hardmax > Identity > InstanceNormalization > Log > LpNormalization > Mul > PRelu > ReduceMax > ReduceSum > Reshape > Shape > Slice > Squeeze > Sub > Sum > Transpose > Unsqueeze > Please refer to the [ONNX Operator > Schemas|[https://github.com/onnx/onnx/blob/master/docs/Operators.md]] for > more detailed information. -- This message was sent by Atlassian JIRA (v7.6.14#76016)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ https://issues.apache.org/jira/browse/SINGA-476?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangzhaoqi updated SINGA-476: -- Attachment: bidaf.png > 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 > Attachments: arcface(based resnet100).png, bidaf.png, tiny_yolov2.png > > > For the demo purpose, we need to implement these three models, and these are > their components: > h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] > MaxPooling2D > Conv2D > BatchNormalization > LeakyReLU > Reshape > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Conv2D > BatchNormalization > relu > MaxPooling2D > Dropout > Flatten > Dense > Softmax > l2_normalize > acos > cos > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ https://issues.apache.org/jira/browse/SINGA-476?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangzhaoqi updated SINGA-476: -- Attachment: arcface(based resnet100).png > 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 > Attachments: arcface(based resnet100).png, tiny_yolov2.png > > > For the demo purpose, we need to implement these three models, and these are > their components: > h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] > MaxPooling2D > Conv2D > BatchNormalization > LeakyReLU > Reshape > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Conv2D > BatchNormalization > relu > MaxPooling2D > Dropout > Flatten > Dense > Softmax > l2_normalize > acos > cos > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ https://issues.apache.org/jira/browse/SINGA-476?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangzhaoqi updated SINGA-476: -- Attachment: tiny_yolov2.png > 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 > Attachments: arcface(based resnet100).png, tiny_yolov2.png > > > For the demo purpose, we need to implement these three models, and these are > their components: > h2. [Tiny yolov2|https://arxiv.org/pdf/1612.08242.pdf] > MaxPooling2D > Conv2D > BatchNormalization > LeakyReLU > Reshape > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Conv2D > BatchNormalization > relu > MaxPooling2D > Dropout > Flatten > Dense > Softmax > l2_normalize > acos > cos > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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|https://arxiv.org/pdf/1612.08242.pdf] MaxPooling2D Conv2D BatchNormalization LeakyReLU Reshape h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Conv2D BatchNormalization relu MaxPooling2D Dropout Flatten Dense Softmax l2_normalize acos cos h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] 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|https://arxiv.org/pdf/1612.08242.pdf] MaxPooling2D Conv2D BatchNormalization LeakyReLU Reshape h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Conv2D BatchNormalization relu MaxPooling2D Dropout Flatten Dense Softmax l2_normalize acos cos h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] 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. > 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|https://arxiv.org/pdf/1612.08242.pdf] > MaxPooling2D > Conv2D > BatchNormalization > LeakyReLU > Reshape > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Conv2D > BatchNormalization > relu > MaxPooling2D > Dropout > Flatten > Dense > Softmax > l2_normalize > acos > cos > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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|https://arxiv.org/pdf/1612.08242.pdf] MaxPooling2D Conv2D BatchNormalization LeakyReLU Reshape h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] Conv2D BatchNormalization relu MaxPooling2D Dropout Flatten Dense Softmax l2_normalize acos cos h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] 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|https://arxiv.org/pdf/1612.08242.pdf] MaxPooling2D Conv2D BatchNormalization LeakyReLU Reshape h2. [Arcface]|https://arxiv.org/pdf/1801.07698.pdf] Conv2D BatchNormalization relu MaxPooling2D Dropout Flatten Dense Softmax l2_normalize acos cos h2. [BIDAF]]|https://arxiv.org/pdf/1611.01603.pdf] 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. > 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|https://arxiv.org/pdf/1612.08242.pdf] > MaxPooling2D > Conv2D > BatchNormalization > LeakyReLU > Reshape > h2. [Arcface|https://arxiv.org/pdf/1801.07698.pdf] > Conv2D > BatchNormalization > relu > MaxPooling2D > Dropout > Flatten > Dense > Softmax > l2_normalize > acos > cos > h2. [BIDAF|https://arxiv.org/pdf/1611.01603.pdf] > 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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|https://arxiv.org/pdf/1612.08242.pdf] MaxPooling2D Conv2D BatchNormalization LeakyReLU Reshape h2. [Arcface]|https://arxiv.org/pdf/1801.07698.pdf] Conv2D BatchNormalization relu MaxPooling2D Dropout Flatten Dense Softmax l2_normalize acos cos h2. [BIDAF]]|https://arxiv.org/pdf/1611.01603.pdf] 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|]|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. > 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|https://arxiv.org/pdf/1612.08242.pdf] > MaxPooling2D > Conv2D > BatchNormalization > LeakyReLU > Reshape > h2. [Arcface]|https://arxiv.org/pdf/1801.07698.pdf] > Conv2D > BatchNormalization > relu > MaxPooling2D > Dropout > Flatten > Dense > Softmax > l2_normalize > acos > cos > h2. [BIDAF]]|https://arxiv.org/pdf/1611.01603.pdf] > 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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|]|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 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. > 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|]|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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ 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 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. was: Already implemented: -LSTM- -Multiply- -Add- -linear- -relu- -acos- -cos- -LeakyReLU- -Softmax- -MaxPooling2D- -Conv2D- -BatchNormalization- 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 > 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. > -- This message was sent by Atlassian JIRA (v7.6.14#76016)
[jira] [Created] (SINGA-476) Autograd operators for ONNX
zhangzhaoqi created SINGA-476: - Summary: Autograd operators for ONNX Key: SINGA-476 URL: https://issues.apache.org/jira/browse/SINGA-476 Project: Singa Issue Type: New Feature Reporter: zhangzhaoqi Already implemented: -LSTM- -Multiply- -Add- -linear- -relu- -acos- -cos- -LeakyReLU- -Softmax- -MaxPooling2D- -Conv2D- -BatchNormalization- 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)
[jira] [Updated] (SINGA-476) Autograd operators for ONNX
[ https://issues.apache.org/jira/browse/SINGA-476?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangzhaoqi updated SINGA-476: -- Description: Already implemented: -LSTM- -Multiply- -Add- -linear- -relu- -acos- -cos- -LeakyReLU- -Softmax- -MaxPooling2D- -Conv2D- -BatchNormalization- 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: Already implemented: -LSTM- -Multiply- -Add- -linear- -relu- -acos- -cos- -LeakyReLU- -Softmax- -MaxPooling2D- -Conv2D- -BatchNormalization- 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 > > Already implemented: > -LSTM- > -Multiply- > -Add- > -linear- > -relu- > -acos- > -cos- > -LeakyReLU- > -Softmax- > -MaxPooling2D- > -Conv2D- > -BatchNormalization- > > 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)