Merge pull request #8176 from kexinzhao/inf_rnn_encode_decode

Add Inference example and unit test for rnn_encoder_decoder

Author: kexinzhao

paddle/framework/block_desc.cc

@@ -162,9 +162,8 @@ BlockDesc::BlockDesc(const BlockDesc &other, proto::BlockDesc *desc,
     : prog_(prog), desc_(desc) {
   need_update_ = true;
   for (auto &op : other.ops_) {
-    ops_.emplace_back(new OpDesc(*op, this));
+    ops_.emplace_back(new OpDesc(*op->Proto(), prog, this));
   }
-
   for (auto &it : other.vars_) {
     auto *var = new VarDesc(*it.second);
     vars_[it.first].reset(var);

paddle/framework/op_desc.cc

@@ -125,11 +125,10 @@ OpDesc::OpDesc(const proto::OpDesc &desc, ProgramDesc *prog, BlockDesc *block)
   // restore attrs_
   for (const proto::OpDesc::Attr &attr : desc_.attrs()) {
     std::string attr_name = attr.name();
+    // The sub_block referred to by the BLOCK attr hasn't been added
+    // to ProgramDesc class yet, we skip setting BLOCK attr here.
     if (attr.type() != proto::AttrType::BLOCK) {
       attrs_[attr_name] = GetAttrValue(attr);
-    } else {
-      auto bid = attr.block_idx();
-      attrs_[attr_name] = prog->MutableBlock(bid);
     }
   }
   this->block_ = block;

paddle/framework/program_desc.cc

@@ -43,18 +43,37 @@ ProgramDesc::ProgramDesc() {
 
 ProgramDesc::ProgramDesc(const ProgramDesc &o) {
   desc_ = o.desc_;
-
   for (int i = 0; i < desc_.blocks_size(); ++i) {
     auto *block = desc_.mutable_blocks(i);
     blocks_.emplace_back(new BlockDesc(*o.blocks_[i], block, this));
   }
+  for (auto &block : blocks_) {
+    for (auto *op : block->AllOps()) {
+      for (const auto &attr : op->Proto()->attrs()) {
+        if (attr.type() == proto::AttrType::BLOCK) {
+          size_t blk_idx = attr.block_idx();
+          op->SetBlockAttr(attr.name(), *this->MutableBlock(blk_idx));
+        }
+      }
+    }
+  }
 }
 
 ProgramDesc::ProgramDesc(const proto::ProgramDesc &desc) {
   desc_ = desc;
   for (auto &block_desc : *desc_.mutable_blocks()) {
     blocks_.emplace_back(new BlockDesc(this, &block_desc));
   }
+  for (auto &block : blocks_) {
+    for (auto *op : block->AllOps()) {
+      for (const auto &attr : op->Proto()->attrs()) {
+        if (attr.type() == proto::AttrType::BLOCK) {
+          size_t blk_idx = attr.block_idx();
+          op->SetBlockAttr(attr.name(), *this->MutableBlock(blk_idx));
+        }
+      }
+    }
+  }
 }
 
 ProgramDesc::ProgramDesc(const std::string &binary_str) {

paddle/framework/prune.cc

@@ -49,11 +49,28 @@ bool IsTarget(const proto::OpDesc& op_desc) {
   return false;
 }
 
-void prune_impl(const proto::ProgramDesc& input, proto::ProgramDesc* output,
-                int block_id) {
-  // TODO(tonyyang-svail):
-  //    - will change to use multiple blocks for RNN op and Cond Op
+int GetSubBlockIndex(const proto::OpDesc& op_desc) {
+  for (auto& attr : op_desc.attrs()) {
+    if (attr.type() == proto::AttrType::BLOCK) {
+      PADDLE_ENFORCE(attr.has_block_idx());
+      return attr.block_idx();
+    }
+  }
+  return -1;
+}
+
+bool HasSubBlock(const proto::OpDesc& op_desc) {
+  return GetSubBlockIndex(op_desc) > 0;
+}
 
+// block_id is the idx of the current block in the input desc
+// parent_block_id is the idx of the parent of the current block
+// in the output desc, -1 means the current block is global block
+// dependent_vars is passed recursively from the parent block to
+// the child block to help pruning
+void prune_impl(const proto::ProgramDesc& input, proto::ProgramDesc* output,
+                int block_id, int parent_block_id,
+                std::set<std::string>& dependent_vars) {
   auto& block = input.blocks(block_id);
   auto& ops = block.ops();
 
@@ -72,19 +89,16 @@ void prune_impl(const proto::ProgramDesc& input, proto::ProgramDesc* output,
     expect_fetch = (op_desc.type() == kFetchOpType);
   }
 
-  std::set<std::string> dependent_vars;
   std::vector<bool> should_run;
   for (auto op_iter = ops.rbegin(); op_iter != ops.rend(); ++op_iter) {
     auto& op_desc = *op_iter;
-
     if (IsTarget(op_desc) || HasDependentVar(op_desc, dependent_vars)) {
       // insert its input to the dependency graph
       for (auto& var : op_desc.inputs()) {
         for (auto& argu : var.arguments()) {
           dependent_vars.insert(argu);
         }
       }
-
       should_run.push_back(true);
     } else {
       should_run.push_back(false);
@@ -95,45 +109,81 @@ void prune_impl(const proto::ProgramDesc& input, proto::ProgramDesc* output,
   // we reverse the should_run vector
   std::reverse(should_run.begin(), should_run.end());
 
-  *output = input;
-  auto* op_field = output->mutable_blocks(block_id)->mutable_ops();
+  // copy the current block from input to output
+  auto* block_field = output->mutable_blocks();
+  *block_field->Add() = input.blocks(block_id);
+
+  int output_block_id = output->blocks_size() - 1;
+  auto* output_block = output->mutable_blocks(output_block_id);
+  output_block->set_idx(output_block_id);
+  output_block->set_parent_idx(parent_block_id);
+
+  auto* op_field = output_block->mutable_ops();
   op_field->Clear();
   for (size_t i = 0; i < should_run.size(); ++i) {
     if (should_run[i]) {
-      *op_field->Add() = input.blocks(block_id).ops(i);
+      auto* op = op_field->Add();
+      *op = input.blocks(block_id).ops(i);
+      if (HasSubBlock(*op)) {
+        // create sub_block_dependent_vars here to help prune the sub block
+        std::set<std::string> sub_block_dependent_vars;
+        for (auto& var : op->inputs()) {
+          for (auto& argu : var.arguments()) {
+            sub_block_dependent_vars.insert(argu);
+          }
+        }
+        for (auto& var : op->outputs()) {
+          for (auto& argu : var.arguments()) {
+            sub_block_dependent_vars.insert(argu);
+          }
+        }
+        // GetSubBlockIndex(*op) is the idx of the sub_block in the input desc
+        // output_block_id is the idx of the current block in the output desc
+        prune_impl(input, output, GetSubBlockIndex(*op), output_block_id,
+                   sub_block_dependent_vars);
+      }
     }
   }
 
   // remove the VarDescs in BlockDesc that are not referenced in
   // the pruned OpDescs
   std::unordered_map<std::string, proto::VarDesc> var_map;
-  auto* var_field = output->mutable_blocks(block_id)->mutable_vars();
+  auto* var_field = output->mutable_blocks(output_block_id)->mutable_vars();
   for (const auto& var : *var_field) {
     var_map[var.name()] = var;
   }
 
-  var_field->Clear();
+  std::set<std::string> var_names;
   for (const auto& op : *op_field) {
-    // add VarDescs of all input arguments for each OpDesc
     auto& input_field = op.inputs();
     for (auto& input_var : input_field) {
       for (auto& arg : input_var.arguments()) {
-        *var_field->Add() = var_map[arg];
+        if (var_map.count(arg) != 0) {
+          var_names.insert(arg);
+        }
       }
     }
-    // add VarDescs of all output arguments for each OpDesc
     auto& output_field = op.outputs();
     for (auto& output_var : output_field) {
       for (auto& arg : output_var.arguments()) {
-        *var_field->Add() = var_map[arg];
+        if (var_map.count(arg) != 0) {
+          var_names.insert(arg);
+        }
       }
     }
   }
+
+  var_field->Clear();
+  for (const auto& name : var_names) {
+    *var_field->Add() = var_map[name];
+  }
 }
 
 // TODO(fengjiayi): Prune() could be inplaced to avoid unnecessary copies
 void Prune(const proto::ProgramDesc& input, proto::ProgramDesc* output) {
-  prune_impl(input, output, 0);
+  std::set<std::string> dependent_vars;
+  output->clear_blocks();
+  prune_impl(input, output, 0, -1, dependent_vars);
 }
 
 void inference_optimize_impl(const proto::ProgramDesc& input,

paddle/inference/tests/book/CMakeLists.txt

@@ -27,3 +27,4 @@ endfunction(inference_test)
 inference_test(recognize_digits ARGS mlp)
 inference_test(image_classification ARGS vgg resnet)
 inference_test(label_semantic_roles)
+inference_test(rnn_encoder_decoder)

paddle/inference/tests/book/test_inference_rnn_encoder_decoder.cc

@@ -0,0 +1,67 @@
+/* Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserve.
+
+Licensed 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. */
+
+#include <gtest/gtest.h>
+#include "gflags/gflags.h"
+#include "test_helper.h"
+
+DEFINE_string(dirname, "", "Directory of the inference model.");
+
+TEST(inference, rnn_encoder_decoder) {
+  if (FLAGS_dirname.empty()) {
+    LOG(FATAL) << "Usage: ./example --dirname=path/to/your/model";
+  }
+
+  LOG(INFO) << "FLAGS_dirname: " << FLAGS_dirname << std::endl;
+  std::string dirname = FLAGS_dirname;
+
+  // 0. Call `paddle::framework::InitDevices()` initialize all the devices
+  // In unittests, this is done in paddle/testing/paddle_gtest_main.cc
+
+  paddle::framework::LoDTensor word_data, trg_word;
+  paddle::framework::LoD lod{{0, 4, 10}};
+
+  SetupLoDTensor(
+      word_data, lod, static_cast<int64_t>(0), static_cast<int64_t>(1));
+  SetupLoDTensor(
+      trg_word, lod, static_cast<int64_t>(0), static_cast<int64_t>(1));
+
+  std::vector<paddle::framework::LoDTensor*> cpu_feeds;
+  cpu_feeds.push_back(&word_data);
+  cpu_feeds.push_back(&trg_word);
+
+  paddle::framework::LoDTensor output1;
+  std::vector<paddle::framework::LoDTensor*> cpu_fetchs1;
+  cpu_fetchs1.push_back(&output1);
+
+  // Run inference on CPU
+  TestInference<paddle::platform::CPUPlace, float>(
+      dirname, cpu_feeds, cpu_fetchs1);
+  LOG(INFO) << output1.lod();
+  LOG(INFO) << output1.dims();
+
+#ifdef PADDLE_WITH_CUDA
+  paddle::framework::LoDTensor output2;
+  std::vector<paddle::framework::LoDTensor*> cpu_fetchs2;
+  cpu_fetchs2.push_back(&output2);
+
+  // Run inference on CUDA GPU
+  TestInference<paddle::platform::CUDAPlace, float>(
+      dirname, cpu_feeds, cpu_fetchs2);
+  LOG(INFO) << output2.lod();
+  LOG(INFO) << output2.dims();
+
+  CheckError<float>(output1, output2);
+#endif
+}