[ 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)