remove depedence on predictor.clone() (#240)

* remove depedence on predictor.clone()

* remove commented lines

* remove FATAL logging

* remove ESAgent's construnction function based on cxx_config

* mv prototxt

deepes/demo/paddle/cartpole_async_solver.cc

@@ -24,20 +24,6 @@ using namespace paddle::lite_api;
 
 const int ITER = 10;
 
-std::shared_ptr<PaddlePredictor> create_paddle_predictor(const std::string& model_dir) {
-  // 1. Create CxxConfig
-  CxxConfig config;
-  config.set_model_dir(model_dir);
-  config.set_valid_places({
-    Place{TARGET(kX86), PRECISION(kFloat)},
-    Place{TARGET(kHost), PRECISION(kFloat)}
-  });
-
-  // 2. Create PaddlePredictor by CxxConfig
-  std::shared_ptr<PaddlePredictor> predictor = CreatePaddlePredictor<CxxConfig>(config);
-  return predictor;
-}
-
 // Use PaddlePredictor of CartPole model to predict the action.
 std::vector<float> forward(std::shared_ptr<PaddlePredictor> predictor, const float* obs) {
   std::unique_ptr<Tensor> input_tensor(std::move(predictor->GetInput(0)));
@@ -86,8 +72,8 @@ int main(int argc, char* argv[]) {
     envs.push_back(CartPole());
   }
 
-  std::shared_ptr<PaddlePredictor> paddle_predictor = create_paddle_predictor("../demo/paddle/cartpole_init_model");
-  std::shared_ptr<AsyncESAgent> agent = std::make_shared<AsyncESAgent>(paddle_predictor, "../benchmark/cartpole_config.prototxt");
+  std::shared_ptr<AsyncESAgent> agent = std::make_shared<AsyncESAgent>("../demo/paddle/cartpole_init_model",
+      "../demo/cartpole_config.prototxt");
 
   // Clone agents to sample (explore).
   std::vector< std::shared_ptr<AsyncESAgent> > sampling_agents;

deepes/demo/paddle/cartpole_solver_parallel.cc

@@ -24,20 +24,6 @@ using namespace paddle::lite_api;
 
 const int ITER = 10;
 
-std::shared_ptr<PaddlePredictor> create_paddle_predictor(const std::string& model_dir) {
-  // 1. Create CxxConfig
-  CxxConfig config;
-  config.set_model_dir(model_dir);
-  config.set_valid_places({
-    Place{TARGET(kX86), PRECISION(kFloat)},
-    Place{TARGET(kHost), PRECISION(kFloat)}
-  });
-
-  // 2. Create PaddlePredictor by CxxConfig
-  std::shared_ptr<PaddlePredictor> predictor = CreatePaddlePredictor<CxxConfig>(config);
-  return predictor;
-}
-
 // Use PaddlePredictor of CartPole model to predict the action.
 std::vector<float> forward(std::shared_ptr<PaddlePredictor> predictor, const float* obs) {
   std::unique_ptr<Tensor> input_tensor(std::move(predictor->GetInput(0)));
@@ -86,8 +72,8 @@ int main(int argc, char* argv[]) {
     envs.push_back(CartPole());
   }
 
-  std::shared_ptr<PaddlePredictor> paddle_predictor = create_paddle_predictor("../demo/paddle/cartpole_init_model");
-  std::shared_ptr<ESAgent> agent = std::make_shared<ESAgent>(paddle_predictor, "../benchmark/cartpole_config.prototxt");
+  std::shared_ptr<ESAgent> agent = std::make_shared<ESAgent>("../demo/paddle/cartpole_init_model",
+      "../demo/cartpole_config.prototxt");
 
   // Clone agents to sample (explore).
   std::vector< std::shared_ptr<ESAgent> > sampling_agents;

deepes/demo/paddle/gen_cartpole_init_model.py

@@ -36,4 +36,6 @@ if __name__ == '__main__':
         dirname='cartpole_init_model',
         feeded_var_names=['obs'],
         target_vars=[prob],
+        params_filename='param',
+        model_filename='model',
         executor=exe)

deepes/demo/torch/cartpole_solver_parallel.cc

@@ -51,7 +51,8 @@ int main(int argc, char* argv[]) {
   }
 
   auto model = std::make_shared<Model>(4, 2);
-  std::shared_ptr<ESAgent<Model>> agent = std::make_shared<ESAgent<Model>>(model, "../benchmark/cartpole_config.prototxt");
+  std::shared_ptr<ESAgent<Model>> agent = std::make_shared<ESAgent<Model>>(model,
+      "../demo/cartpole_config.prototxt");
   
   // Clone agents to sample (explore).
   std::vector<std::shared_ptr<ESAgent<Model>>> sampling_agents;

deepes/include/paddle/async_es_agent.h

@@ -40,8 +40,8 @@ class AsyncESAgent: public ESAgent {
      * Please use the up-to-date configuration.
      */
   AsyncESAgent(
-      std::shared_ptr<PaddlePredictor> predictor,
-      std::string config_path);
+      const std::string& model_dir,
+      const std::string& config_path);
 
     /**
      * @brief: Clone an agent for sampling.

deepes/include/paddle/es_agent.h

@@ -38,13 +38,11 @@ int64_t ShapeProduction(const shape_t& shape);
  */
 class ESAgent {
  public:
-  ESAgent();
+  ESAgent() {}
 
   ~ESAgent();
 
-  ESAgent(
-      std::shared_ptr<PaddlePredictor> predictor,
-      std::string config_path);
+  ESAgent(const std::string& model_dir, const std::string& config_path);
   
   /** 
    * @breif Clone a sampling agent
@@ -83,15 +81,16 @@ class ESAgent {
 
   std::shared_ptr<PaddlePredictor> _predictor;
   std::shared_ptr<PaddlePredictor> _sampling_predictor;
-  bool _is_sampling_agent;
   std::shared_ptr<SamplingMethod> _sampling_method;
   std::shared_ptr<Optimizer> _optimizer;
   std::shared_ptr<DeepESConfig> _config;
-  int64_t _param_size;
+  std::shared_ptr<CxxConfig> _cxx_config;
   std::vector<std::string> _param_names;
   // malloc memory of noise and neg_gradients in advance.
   float* _noise;
   float* _neg_gradients;
+  int64_t _param_size;
+  bool _is_sampling_agent;
 };
 
 }

deepes/include/utils.h

@@ -20,6 +20,7 @@
 #include <glog/logging.h>
 #include "deepes.pb.h"
 #include <google/protobuf/text_format.h>
+#include <fstream>
 
 namespace DeepES{
 
@@ -29,6 +30,8 @@ namespace DeepES{
 */
 bool compute_centered_ranks(std::vector<float> &reward);
 
+std::string read_file(const std::string& filename);
+
 /* Load a protobuf-based configuration from the file.
  * Args:
  *  config_file: file path.

deepes/src/paddle/async_es_agent.cc

@@ -16,8 +16,8 @@
 namespace DeepES {
 
 AsyncESAgent::AsyncESAgent(
-    std::shared_ptr<PaddlePredictor> predictor,
-    std::string config_path): ESAgent(predictor, config_path) {
+    const std::string& model_dir,
+    const std::string& config_path): ESAgent(model_dir, config_path) {
   _config_path = config_path;
 }
 AsyncESAgent::~AsyncESAgent() {
@@ -155,15 +155,13 @@ std::shared_ptr<PaddlePredictor> AsyncESAgent::_load_previous_model(std::string
 }
 
 std::shared_ptr<AsyncESAgent> AsyncESAgent::clone() {
-  std::shared_ptr<PaddlePredictor> new_sampling_predictor = _predictor->Clone();
 
   std::shared_ptr<AsyncESAgent> new_agent = std::make_shared<AsyncESAgent>();
 
   float* noise = new float [_param_size];
 
   new_agent->_predictor = _predictor;
-  new_agent->_sampling_predictor = new_sampling_predictor;
-
+  new_agent->_sampling_predictor = CreatePaddlePredictor<CxxConfig>(*_cxx_config);
   new_agent->_is_sampling_agent = true;
   new_agent->_sampling_method = _sampling_method;
   new_agent->_param_names = _param_names;

deepes/src/paddle/es_agent.cc

@@ -23,22 +23,31 @@ int64_t ShapeProduction(const shape_t& shape) {
   return res;
 }
 
-ESAgent::ESAgent() {}
-
 ESAgent::~ESAgent() {
   delete[] _noise;
   if (!_is_sampling_agent)
     delete[] _neg_gradients;
 }
 
-ESAgent::ESAgent(
-    std::shared_ptr<PaddlePredictor> predictor,
-    std::string config_path) {
+ESAgent::ESAgent(const std::string& model_dir, const std::string& config_path) {
+  // 1. Create CxxConfig
+  _cxx_config = std::make_shared<CxxConfig>();
+  std::string model_path = model_dir + "/model";
+  std::string param_path = model_dir + "/param";
+  std::string model_buffer = read_file(model_path);
+  std::string param_buffer = read_file(param_path);
+	_cxx_config->set_model_buffer(model_buffer.c_str(), model_buffer.size(), 
+      param_buffer.c_str(), param_buffer.size());
+  _cxx_config->set_valid_places({
+    Place{TARGET(kX86), PRECISION(kFloat)},
+    Place{TARGET(kHost), PRECISION(kFloat)}
+  });
+
+  _predictor = CreatePaddlePredictor<CxxConfig>(*_cxx_config);
 
   _is_sampling_agent = false;
-  _predictor = predictor;
   // Original agent can't be used to sample, so keep it same with _predictor for evaluating.
-  _sampling_predictor = predictor;
+  _sampling_predictor = _predictor;
 
   _config = std::make_shared<DeepESConfig>();
   load_proto_conf(config_path, *_config);
@@ -56,15 +65,17 @@ ESAgent::ESAgent(
 }
 
 std::shared_ptr<ESAgent> ESAgent::clone() {
-  std::shared_ptr<PaddlePredictor> new_sampling_predictor = _predictor->Clone();
-
+  if (_is_sampling_agent) {
+    LOG(ERROR) << "[DeepES] only original ESAgent can call `clone` function.";
+    return nullptr;
+  }
   std::shared_ptr<ESAgent> new_agent = std::make_shared<ESAgent>();
 
   float* noise = new float [_param_size];
 
+  new_agent->_sampling_predictor = CreatePaddlePredictor<CxxConfig>(*_cxx_config);
   new_agent->_predictor = _predictor;
-  new_agent->_sampling_predictor = new_sampling_predictor;
-
+  new_agent->_cxx_config = _cxx_config;
   new_agent->_is_sampling_agent = true;
   new_agent->_sampling_method = _sampling_method;
   new_agent->_param_names = _param_names;

deepes/src/utils.cc

@@ -52,4 +52,17 @@ std::vector<std::string> list_all_model_dirs(std::string path) {
   return model_dirs;
 }
 
+std::string read_file(const std::string& filename) {
+  std::ifstream ifile(filename.c_str());
+  if (!ifile.is_open()) {
+    LOG(ERROR) << "Open file: [" << filename << "] failed.";
+    return "";
+  }
+  std::ostringstream buf;
+  char ch;
+  while (buf && ifile.get(ch)) buf.put(ch);
+  ifile.close();
+  return buf.str();
+}
+
 }//namespace