Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* GELU activation * GELU derivative * GELU wrappers * optional PI definition * fast gelu & derivative
- Loading branch information
Showing
6 changed files
with
227 additions
and
9 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
77 changes: 77 additions & 0 deletions
77
...pi-parent/nd4j-api/src/main/java/org/nd4j/linalg/api/ops/impl/transforms/strict/GELU.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,77 @@ | ||
| /******************************************************************************* | ||
| * Copyright (c) 2015-2018 Skymind, Inc. | ||
| * | ||
| * This program and the accompanying materials are made available under the | ||
| * terms of the Apache License, Version 2.0 which is available at | ||
| * https://www.apache.org/licenses/LICENSE-2.0. | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT | ||
| * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the | ||
| * License for the specific language governing permissions and limitations | ||
| * under the License. | ||
| * | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| ******************************************************************************/ | ||
|
|
||
| package org.nd4j.linalg.api.ops.impl.transforms.strict; | ||
|
|
||
| import org.nd4j.autodiff.samediff.SDVariable; | ||
| import org.nd4j.autodiff.samediff.SameDiff; | ||
| import org.nd4j.imports.NoOpNameFoundException; | ||
| import org.nd4j.linalg.api.ndarray.INDArray; | ||
| import org.nd4j.linalg.api.ops.BaseTransformStrictOp; | ||
|
|
||
| import java.util.Arrays; | ||
| import java.util.List; | ||
|
|
||
| /** | ||
| * GELU function | ||
| * | ||
| * @author raver119@gmail.com | ||
| */ | ||
| public class GELU extends BaseTransformStrictOp { | ||
| public GELU(SameDiff sameDiff, SDVariable i_v, boolean inPlace) { | ||
| super(sameDiff, i_v, inPlace); | ||
| } | ||
|
|
||
| public GELU() { | ||
| } | ||
|
|
||
| public GELU(INDArray x, INDArray z) { | ||
| super(x, z); | ||
| } | ||
|
|
||
| public GELU(INDArray ndArray) { | ||
| super(ndArray); | ||
| } | ||
|
|
||
| @Override | ||
| public int opNum() { | ||
| return 53; | ||
| } | ||
|
|
||
| @Override | ||
| public String opName() { | ||
| return "gelu"; | ||
| } | ||
|
|
||
| @Override | ||
| public String onnxName() { | ||
| throw new NoOpNameFoundException("No onnx op opName found for " + opName()); | ||
| } | ||
|
|
||
| @Override | ||
| public String tensorflowName() { | ||
| return "GELU"; | ||
| } | ||
|
|
||
|
|
||
| @Override | ||
| public List<SDVariable> doDiff(List<SDVariable> i_v) { | ||
| SDVariable ret = f().geluDerivative(arg()).mul(i_v.get(0)); | ||
| return Arrays.asList(ret); | ||
| } | ||
|
|
||
|
|
||
| } |
79 changes: 79 additions & 0 deletions
79
...nd4j-api/src/main/java/org/nd4j/linalg/api/ops/impl/transforms/strict/GELUDerivative.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,79 @@ | ||
| /******************************************************************************* | ||
| * Copyright (c) 2015-2018 Skymind, Inc. | ||
| * | ||
| * This program and the accompanying materials are made available under the | ||
| * terms of the Apache License, Version 2.0 which is available at | ||
| * https://www.apache.org/licenses/LICENSE-2.0. | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT | ||
| * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the | ||
| * License for the specific language governing permissions and limitations | ||
| * under the License. | ||
| * | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| ******************************************************************************/ | ||
|
|
||
| package org.nd4j.linalg.api.ops.impl.transforms.strict; | ||
|
|
||
| import org.nd4j.autodiff.samediff.SDVariable; | ||
| import org.nd4j.autodiff.samediff.SameDiff; | ||
| import org.nd4j.imports.NoOpNameFoundException; | ||
| import org.nd4j.linalg.api.ndarray.INDArray; | ||
| import org.nd4j.linalg.api.ops.BaseTransformStrictOp; | ||
|
|
||
| import java.util.List; | ||
|
|
||
| /** | ||
| * GELU derivative | ||
| * | ||
| * @author Adam Gibson | ||
| */ | ||
| public class GELUDerivative extends BaseTransformStrictOp { | ||
| public GELUDerivative(SameDiff sameDiff, SDVariable i_v1, SDVariable i_v2) { | ||
| super(sameDiff, i_v1, i_v2); | ||
| } | ||
|
|
||
| public GELUDerivative(SameDiff sameDiff, SDVariable i_v1, SDVariable i_v2, boolean inPlace) { | ||
| super(sameDiff, i_v1, i_v2, inPlace); | ||
| } | ||
|
|
||
| public GELUDerivative(SameDiff sameDiff, SDVariable i_v, boolean inPlace) { | ||
| super(sameDiff, i_v, inPlace); | ||
| } | ||
|
|
||
| public GELUDerivative() {} | ||
|
|
||
| public GELUDerivative(INDArray x, INDArray z) { | ||
| super(x, z); | ||
| } | ||
|
|
||
| public GELUDerivative(INDArray x) { | ||
| super(x); | ||
| } | ||
|
|
||
| @Override | ||
| public int opNum() { | ||
| return 54; | ||
| } | ||
|
|
||
| @Override | ||
| public String opName() { | ||
| return "_geluderivative"; | ||
| } | ||
|
|
||
| @Override | ||
| public String onnxName() { | ||
| throw new NoOpNameFoundException("No onnx op opName found for " + opName()); | ||
| } | ||
|
|
||
| @Override | ||
| public String tensorflowName() { | ||
| throw new NoOpNameFoundException("No tensorflow op opName found for " + opName()); | ||
| } | ||
|
|
||
| @Override | ||
| public List<SDVariable> doDiff(List<SDVariable> f1) { | ||
| throw new UnsupportedOperationException(); | ||
| } | ||
| } |