lstmtraining.cpp File Reference

#include <cerrno>
#include "commontraining.h"
#include "fileio.h"
#include "lstmtester.h"
#include "lstmtrainer.h"
#include "params.h"
#include <tesseract/strngs.h>
#include "tprintf.h"
#include "unicharset_training_utils.h"

Go to the source code of this file.

Functions
int	main (int argc, char **argv)

Variables
const int	kNumPagesPerBatch = 100

Function Documentation

main()

int main	(	int	argc,
		char **	argv
	)

Definition at line 74 of file lstmtraining.cpp.

                                {
  tesseract::CheckSharedLibraryVersion();
  ParseArguments(&argc, &argv);
  if (FLAGS_model_output.empty()) {
    tprintf("Must provide a --model_output!\n");
    return EXIT_FAILURE;
  }
  if (FLAGS_traineddata.empty()) {
    tprintf("Must provide a --traineddata see training wiki\n");
    return EXIT_FAILURE;
  }
 
  // Check write permissions.
  STRING test_file = FLAGS_model_output.c_str();
  test_file += "_wtest";
  FILE* f = fopen(test_file.c_str(), "wb");
  if (f != nullptr) {
    fclose(f);
    if (remove(test_file.c_str()) != 0) {
      tprintf("Error, failed to remove %s: %s\n",
              test_file.c_str(), strerror(errno));
      return EXIT_FAILURE;
    }
  } else {
    tprintf("Error, model output cannot be written: %s\n", strerror(errno));
    return EXIT_FAILURE;
  }
 
  // Setup the trainer.
  STRING checkpoint_file = FLAGS_model_output.c_str();
  checkpoint_file += "_checkpoint";
  STRING checkpoint_bak = checkpoint_file + ".bak";
  tesseract::LSTMTrainer trainer(
      FLAGS_model_output.c_str(),
      checkpoint_file.c_str(), FLAGS_debug_interval,
      static_cast<int64_t>(FLAGS_max_image_MB) * 1048576);
  trainer.InitCharSet(FLAGS_traineddata.c_str());
 
  // Reading something from an existing model doesn't require many flags,
  // so do it now and exit.
  if (FLAGS_stop_training || FLAGS_debug_network) {
    if (!trainer.TryLoadingCheckpoint(FLAGS_continue_from.c_str(), nullptr)) {
      tprintf("Failed to read continue from: %s\n",
              FLAGS_continue_from.c_str());
      return EXIT_FAILURE;
    }
    if (FLAGS_debug_network) {
      trainer.DebugNetwork();
    } else {
      if (FLAGS_convert_to_int) trainer.ConvertToInt();
      if (!trainer.SaveTraineddata(FLAGS_model_output.c_str())) {
        tprintf("Failed to write recognition model : %s\n",
                FLAGS_model_output.c_str());
      }
    }
    return EXIT_SUCCESS;
  }
 
  // Get the list of files to process.
  if (FLAGS_train_listfile.empty()) {
    tprintf("Must supply a list of training filenames! --train_listfile\n");
    return EXIT_FAILURE;
  }
  GenericVector<STRING> filenames;
  if (!tesseract::LoadFileLinesToStrings(FLAGS_train_listfile.c_str(),
                                         &filenames)) {
    tprintf("Failed to load list of training filenames from %s\n",
            FLAGS_train_listfile.c_str());
    return EXIT_FAILURE;
  }
 
  // Checkpoints always take priority if they are available.
  if (trainer.TryLoadingCheckpoint(checkpoint_file.c_str(), nullptr) ||
      trainer.TryLoadingCheckpoint(checkpoint_bak.c_str(), nullptr)) {
    tprintf("Successfully restored trainer from %s\n",
            checkpoint_file.c_str());
  } else {
    if (!FLAGS_continue_from.empty()) {
      // Load a past model file to improve upon.
      if (!trainer.TryLoadingCheckpoint(FLAGS_continue_from.c_str(),
                                        FLAGS_append_index >= 0
                                            ? FLAGS_continue_from.c_str()
                                            : FLAGS_old_traineddata.c_str())) {
        tprintf("Failed to continue from: %s\n", FLAGS_continue_from.c_str());
        return EXIT_FAILURE;
      }
      tprintf("Continuing from %s\n", FLAGS_continue_from.c_str());
      trainer.InitIterations();
    }
    if (FLAGS_continue_from.empty() || FLAGS_append_index >= 0) {
      if (FLAGS_append_index >= 0) {
        tprintf("Appending a new network to an old one!!");
        if (FLAGS_continue_from.empty()) {
          tprintf("Must set --continue_from for appending!\n");
          return EXIT_FAILURE;
        }
      }
      // We are initializing from scratch.
      if (!trainer.InitNetwork(FLAGS_net_spec.c_str(), FLAGS_append_index,
                               FLAGS_net_mode, FLAGS_weight_range,
                               FLAGS_learning_rate, FLAGS_momentum,
                               FLAGS_adam_beta)) {
        tprintf("Failed to create network from spec: %s\n",
                FLAGS_net_spec.c_str());
        return EXIT_FAILURE;
      }
      trainer.set_perfect_delay(FLAGS_perfect_sample_delay);
    }
  }
  if (!trainer.LoadAllTrainingData(filenames,
                                   FLAGS_sequential_training
                                       ? tesseract::CS_SEQUENTIAL
                                       : tesseract::CS_ROUND_ROBIN,
                                   FLAGS_randomly_rotate)) {
    tprintf("Load of images failed!!\n");
    return EXIT_FAILURE;
  }
 
  tesseract::LSTMTester tester(static_cast<int64_t>(FLAGS_max_image_MB) *
                               1048576);
  tesseract::TestCallback tester_callback = nullptr;
  if (!FLAGS_eval_listfile.empty()) {
    using namespace std::placeholders;  // for _1, _2, _3...
    if (!tester.LoadAllEvalData(FLAGS_eval_listfile.c_str())) {
      tprintf("Failed to load eval data from: %s\n",
              FLAGS_eval_listfile.c_str());
      return EXIT_FAILURE;
    }
    tester_callback = std::bind(&tesseract::LSTMTester::RunEvalAsync, &tester, _1, _2, _3, _4);
  }
  do {
    // Train a few.
    int iteration = trainer.training_iteration();
    for (int target_iteration = iteration + kNumPagesPerBatch;
         iteration < target_iteration &&
         (iteration < FLAGS_max_iterations || FLAGS_max_iterations == 0);
         iteration = trainer.training_iteration()) {
      trainer.TrainOnLine(&trainer, false);
    }
    STRING log_str;
    trainer.MaintainCheckpoints(tester_callback, &log_str);
    tprintf("%s\n", log_str.c_str());
  } while (trainer.best_error_rate() > FLAGS_target_error_rate &&
           (trainer.training_iteration() < FLAGS_max_iterations ||
            FLAGS_max_iterations == 0));
  tprintf("Finished! Error rate = %g\n", trainer.best_error_rate());
  return EXIT_SUCCESS;
} /* main */

Variable Documentation

kNumPagesPerBatch

const int kNumPagesPerBatch = 100

Definition at line 68 of file lstmtraining.cpp.