This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
MXNet Extensions enhancements2 #19016
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -24,7 +24,7 @@ | |
| */ | ||
|
|
||
| #include <iostream> | ||
| #include "mxnet/lib_api.h" | ||
|
|
||
| using namespace mxnet::ext; | ||
|
|
||
|
|
||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -25,7 +25,7 @@ | |
|
|
||
| #include <iostream> | ||
| #include <utility> | ||
| #include "mxnet/lib_api.h" | ||
|
|
||
| using namespace mxnet::ext; | ||
|
|
||
|
|
||
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 +1,171 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one | ||
| * or more contributor license agreements. See the NOTICE file | ||
| * distributed with this work for additional information | ||
| * regarding copyright ownership. The ASF licenses this file | ||
| * to you under the Apache License, Version 2.0 (the | ||
| * "License"); you may not use this file except in compliance | ||
| * with the License. You may obtain a copy of the License at | ||
| * | ||
| * http://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. | ||
| */ | ||
|
|
||
| /*! | ||
| * Copyright (c) 2020 by Contributors | ||
| * \file relu_lib.cu | ||
| * \brief simple custom relu and noisy relu operator implemented using CUDA function | ||
| */ | ||
|
|
||
| #include <iostream> | ||
| #include "relu_lib.h" | ||
|
|
||
| using namespace mxnet::ext; | ||
|
|
||
| MXReturnValue parseAttrs(const std::unordered_map<std::string, std::string>& attrs, | ||
| int* num_in, int* num_out) { | ||
| *num_in = 1; | ||
| *num_out = 1; | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| MXReturnValue inferType(const std::unordered_map<std::string, std::string>& attrs, | ||
| std::vector<int>* intypes, | ||
| std::vector<int>* outtypes) { | ||
| outtypes->at(0) = intypes->at(0); | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| MXReturnValue inferShape(const std::unordered_map<std::string, std::string>& attrs, | ||
| std::vector<std::vector<unsigned int>>* inshapes, | ||
| std::vector<std::vector<unsigned int>>* outshapes) { | ||
| outshapes->at(0) = inshapes->at(0); | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| MXReturnValue forwardCPU(const std::unordered_map<std::string, std::string>& attrs, | ||
| std::vector<MXTensor>* inputs, | ||
| std::vector<MXTensor>* outputs, | ||
| const OpResource& res) { | ||
| float* in_data = inputs->at(0).data<float>(); | ||
| float* out_data = outputs->at(0).data<float>(); | ||
| for (int i=0; i<inputs->at(0).size(); i++) { | ||
| out_data[i] = in_data[i] > 0 ? in_data[i] : 0; | ||
| } | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| MXReturnValue backwardCPU(const std::unordered_map<std::string, std::string>& attrs, | ||
| std::vector<MXTensor>* inputs, | ||
| std::vector<MXTensor>* outputs, | ||
| const OpResource& res) { | ||
| float* out_grad = inputs->at(0).data<float>(); | ||
| float* in_data = inputs->at(1).data<float>(); | ||
| float* in_grad = outputs->at(0).data<float>(); | ||
| for (int i=0; i<inputs->at(1).size(); i++) { | ||
| in_grad[i] = in_data[i] > 0 ? 1 * out_grad[i] : 0; | ||
| } | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| REGISTER_OP(my_relu) | ||
| .setParseAttrs(parseAttrs) | ||
| .setInferType(inferType) | ||
| .setInferShape(inferShape) | ||
| .setForward(forwardCPU, "cpu") | ||
| .setForward(forwardGPU, "gpu") | ||
| .setBackward(backwardCPU, "cpu") | ||
| .setBackward(backwardGPU, "gpu"); | ||
|
|
||
|
|
||
| MyStatefulReluCPU::MyStatefulReluCPU(const std::unordered_map<std::string, std::string>& attrs) | ||
| : attrs_(attrs) {} | ||
|
|
||
| MXReturnValue MyStatefulReluCPU::Forward(std::vector<MXTensor>* inputs, | ||
| std::vector<MXTensor>* outputs, | ||
| const OpResource& op_res) { | ||
| return forwardCPU(attrs_, inputs, outputs, op_res); | ||
| } | ||
|
|
||
| MXReturnValue MyStatefulReluCPU::Backward(std::vector<MXTensor>* inputs, | ||
| std::vector<MXTensor>* outputs, | ||
| const OpResource& op_res) { | ||
| return backwardCPU(attrs_, inputs, outputs, op_res); | ||
| } | ||
|
|
||
| MyStatefulReluGPU::MyStatefulReluGPU(const std::unordered_map<std::string, std::string>& attrs) | ||
| : attrs_(attrs) {} | ||
|
|
||
| MXReturnValue MyStatefulReluGPU::Forward(std::vector<MXTensor>* inputs, | ||
| std::vector<MXTensor>* outputs, | ||
| const OpResource& op_res) { | ||
| return forwardGPU(attrs_, inputs, outputs, op_res); | ||
| } | ||
|
|
||
| MXReturnValue MyStatefulReluGPU::Backward(std::vector<MXTensor>* inputs, | ||
| std::vector<MXTensor>* outputs, | ||
| const OpResource& op_res) { | ||
| return backwardGPU(attrs_, inputs, outputs, op_res); | ||
| } | ||
|
|
||
|
|
||
| MXReturnValue createOpStateCPU(const std::unordered_map<std::string, std::string>& attrs, | ||
| CustomStatefulOp** op_inst) { | ||
| *op_inst = new MyStatefulReluCPU(attrs); | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| MXReturnValue createOpStateGPU(const std::unordered_map<std::string, std::string>& attrs, | ||
| CustomStatefulOp** op_inst) { | ||
| *op_inst = new MyStatefulReluGPU(attrs); | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| REGISTER_OP(my_state_relu) | ||
| .setParseAttrs(parseAttrs) | ||
| .setInferType(inferType) | ||
| .setInferShape(inferShape) | ||
| .setCreateOpState(createOpStateCPU, "cpu") | ||
| .setCreateOpState(createOpStateGPU, "gpu"); | ||
|
|
||
| MXReturnValue noisyForwardCPU(const std::unordered_map<std::string, std::string>& attrs, | ||
| std::vector<MXTensor>* inputs, | ||
| std::vector<MXTensor>* outputs, | ||
| const OpResource& res) { | ||
| float* in_data = inputs->at(0).data<float>(); | ||
| float* out_data = outputs->at(0).data<float>(); | ||
|
|
||
| mx_cpu_rand_t* states = res.get_cpu_rand_states(); | ||
| std::normal_distribution<float> dist_normal; | ||
|
|
||
| for (int i=0; i<inputs->at(0).size(); ++i) { | ||
| float noise = dist_normal(*states); | ||
| out_data[i] = in_data[i] + noise > 0 ? in_data[i] + noise : 0; | ||
| } | ||
| return MX_SUCCESS; | ||
| } | ||
|
|
||
| REGISTER_OP(my_noisy_relu) | ||
| .setParseAttrs(parseAttrs) | ||
| .setInferType(inferType) | ||
| .setInferShape(inferShape) | ||
| .setForward(noisyForwardCPU, "cpu") | ||
| .setForward(noisyForwardGPU, "gpu") | ||
| .setBackward(backwardCPU, "cpu") | ||
| .setBackward(backwardGPU, "gpu"); | ||
|
|
||
| MXReturnValue initialize(int version) { | ||
| if (version >= 20000) { | ||
|
There was a problem hiding this comment. are you sure about this? since gemm_lib is still 10700 There was a problem hiding this comment. Yes, we should update all the examples to 20000 on master. ill do that in the next PR. There was a problem hiding this comment. discussed offline and we will change example corresponding to master |
||
| std::cout << "MXNet version " << version << " supported" << std::endl; | ||
| return MX_SUCCESS; | ||
| } else { | ||
| MX_ERROR_MSG << "MXNet version " << version << " not supported"; | ||
| return MX_FAIL; | ||
| } | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Offline discussion with @leezu, in another PR we should move this build code into CMakeLists.txt for each example and use
add_subdirectoryto include it and replace the current Makefiles so theres only 1 set of build steps for each example.