#ifndef TRAIN_IMAGE_INC_CPP
#define TRAIN_IMAGE_INC_CPP


#include "train.inc.cpp"
#include "layer.simple.inc.cpp"


class TrainerImage: public Trainer {
protected:
  std::vector<unsigned char> data;
  std::vector<unsigned int> shuffle;
  const char *datafile;
  const char *outfile;
  Layout ofl, obl;
  Layout::List oflist, oblist;
  int stride, count;

public:
  TrainerImage(): stride(), count() { }

  bool configure(const char *datafile, const char *outfile) {
    this->datafile = datafile;
    this->outfile = outfile;
  }
    
    data.clear();

    FILE *f = fopen(filename, "rb");
    if (!f)
      return printf("cannot open file for read: %s\n", filename), false;
    fseek(f, 0, SEEK_END);
    size_t fs = ftello(f);
    fseek(f, 0, SEEK_SET);

    data.resize(fs, 0);
    if (!fread(data.data(), fs, 1, f))
      return printf("cannot read from file: %s\n", filename), fclose(f), data.clear(), false;

    fclose(f);
    return true;
  }

  
void imgTrain(Layer &l, const char *datafile, int size, const char *outfile, double trainRatio, int count) {
  Layer &bl = l.back();

  assert(!l.prev);
  assert(datafile);
  assert(count > 0 && size > 0);
  assert(l.size == size);
  assert(bl.size == size);

  int blockSize = 1000;//1024*1024*1024/size;
  assert(blockSize > 0);

  FILE *f = fopen(datafile, "rb");
  if (!f)
    { printf("cannot open file: %s\n", datafile); return; }
  fseeko64(f, 0, SEEK_END);
  long long fsize = ftello64(f);
  int xCount = (int)(fsize/size);
  if (xCount <= 0)
    { printf("no tests in file: %s\n", datafile); return; }

  int *block = new int[blockSize*2];
  int *shuffle = block + blockSize;
  double *results = new double[blockSize];
  unsigned char *blockData = new unsigned char[(blockSize + 1)*size];
  unsigned char *blockResData = blockData + blockSize*size;
  bool err = false;

  for(int j = 0; j < blockSize; ++j)
    { shuffle[j] = j; results[j] = 0; }

  int blocksCount = (count - 1)/blockSize + 1;

  printf("training %d (%d x %d blocks), tests: %d, ratio: %f:\n", blocksCount*blockSize, blocksCount, blockSize, xCount, trainRatio);

  double avgSum = 0;
  for(int i = 0; i < blocksCount; ++i) {
    for(int j = 0; j < blockSize; ++j) {
      block[j] = rand()%xCount;
      std::swap(shuffle[i], shuffle[rand()%blockSize]);
    }
    std::sort(block, block + blockSize);

    for(int j = 0; j < blockSize; ++j) {
      fseeko64(f, block[j]*(long long)size, SEEK_SET);
      if (!fread(blockData + j*size, size, 1, f))
        { printf("cannot read data from file: %s\n", datafile); err = true; break; }
    }
    if (err) break;

    printf("  next data block loaded\n");

    double sumQ = 0;
    for(int j = 0; j < blockSize; ++j) {
      unsigned char *data = blockData + shuffle[j]*size;
      for(double *ia = l.a, *e = ia + l.size; ia < e; ++ia, ++data)
        *ia = *data/255.0;

      double firstQ = 0, q = 0;
      for(int repeat = 0; repeat < 1; ++repeat) {
        l.pass();

        for(double *ia = l.a, *iba = bl.a, *ibda = bl.da, *e = ia + l.size; ia < e; ++ia, ++iba, ++ibda) {
          double d = *ia - *iba;
          *ibda = d;
          q += d*d;
        }
        q /= size;
        if (!repeat) firstQ = q;

        bl.backpass(trainRatio);
      }

      sumQ += firstQ;
      avgSum += firstQ - results[j];
      results[j] = firstQ;
      int avgCnt = i ? blockSize : j + 1;
      printf("  %4d: total: %6d, avg result: %f, last result: %f -> %f\n", j+1, i*blockSize+j+1, avgSum/avgCnt, firstQ, q);
    }

    printf("%4d: total: %6d, avg result: %f\n", i+1, (i+1)*blockSize, sumQ/blockSize);

    if (outfile && !l.save(outfile))
      { printf("cannot save neural network weights to file: %s\n", outfile); err = true; break; }

    unsigned char *data = blockResData;
    for(double *iba = bl.a, *e = iba + bl.size; iba < e; ++iba, ++data)
      *data = (unsigned char)(*iba*255.999);
    tgaSave("data/output/sampleX.tga", blockData + shuffle[blockSize-1]*size, 256, 256, 3);
    tgaSave("data/output/sampleY.tga", blockResData, 256, 256, 3);
  }

  delete[] block;
  delete[] results;
  delete[] blockData;

  printf("finished\n");
}
  

protected:
  bool prepare() override {
    ofl = optimizeLayoutSimple(fl->layout);
    obl = optimizeLayoutSimple(bl->layout);
    assert(ofl && obl);
    assert(ofl.getActiveCount() == obl.getActiveCount());
    
    ofl.split(oflist, threadsCount);
    obl.split(oblist, threadsCount);
    stride = ofl.getActiveCount() + 1;
    count = data.size()/stride;
    if (count <= 0) return false;
    shuffle.resize(count);
    for(int i = 0; i < count; ++i)
      shuffle[i] = i;
    return true;
  }


  bool prepareBlock() override {
    int cnt = itersPerBlock > count ? count : itersPerBlock;
    for(int i = 0; i < cnt; ++i) {
      int j = rand()%count;
      if (i != j) std::swap(shuffle[i], shuffle[j]);
    }
    return true;
  }


  void loadData(Barrier &barrier, int, int iter) override {
    struct I: public Iter {
      typedef const unsigned char* Type;
      static inline void iter4(Neuron &n, Type d, AccumType&) { n.v = *d/(NeuronReal)255; }
    };
    const unsigned char *id = data.data() + shuffle[iter%count]*stride;
    iterateNeurons2<I>(oflist[barrier.tid], ofl, fl->neurons, id);
  }


  AccumReal verifyDataMain(int, int iter) override {
    struct I: public Iter {
      typedef int Type;
      struct AccumType { int ri, mi; NeuronReal m; };
      static inline void iter4(Neuron &n, Type d, AccumType &a) {
        NeuronReal v1 = d == a.ri;
        NeuronReal v0 = n.v;
        n.d *= v1 - v0;
        if (a.m < v0) { a.m = v0; a.mi = d; }
      }
    };
    
    I::AccumType a = { data[ (shuffle[iter%count] + 1)*stride - 1 ], 0, 0 };
    iterateNeurons2<I>(obl, obl, bl->neurons, 0, 1, &a);
    
    return a.mi != a.ri;
  }
};


#endif