public void save(string file_path_name)
{
FileStream stream = new FileStream(file_path_name, FileMode.Create);
BinaryWriter writer = new BinaryWriter(stream);
WeightLayerPool.save(writer);
writer.Write(UnitLayers.Count);
foreach (UnitLayer layer in UnitLayers.Values)
{
writer.Write(layer.Id);
writer.Write(layer.Depth);
writer.Write(layer.Width);
writer.Write(layer.Height);
}
writer.Close();
stream.Close();
}
public void load(string file_path_name)
{
FileStream stream = new FileStream(file_path_name, FileMode.Open);
BinaryReader reader = new BinaryReader(stream);
WeightLayerPool.load(reader);
int count = reader.ReadInt32();
for (int i = 0; i < count; i++)
{
string id = reader.ReadString();
int depth = reader.ReadInt32();
int width = reader.ReadInt32();
int height = reader.ReadInt32();
UnitLayer layer = new UnitLayer(id, width, height, depth);
UnitLayers.Add(id, layer);
}
reader.Close();
stream.Close();
}
private void forward_convolute_on_depth(UnitLayer to, int stride, int depth, int length)
{
int to_depth = depth + length;
if (to_depth >= to.Depth)
{
to_depth = to.Depth;
}
for (int d = depth; d < to_depth; d++)
{
WeightLayer weights = WeightLayerPool.find(Id, to.Id, d);
int width_of_weights = weights.Width, height_of_weights = weights.Height;
int width_of_units = to.Width, height_of_units = to.Height;
for (int y = 0; y < height_of_units; y++)
{
int top = y * stride;
int bottom = top + height_of_weights;
for (int x = 0; x < width_of_units; x++)
{
int left = x * stride;
to.set_value_at_inport(x, y, d, weights.convolute_product(left, top, left + width_of_weights, bottom, Units));
}
}
}
}
private void backward_convolute_on_depth(UnitLayer to, int stride, int depth, int length)
{
int to_depth = depth + length;
if (to_depth >= Depth)
{
to_depth = Depth;
}
for (int d = depth; d < to_depth; d++)
{
WeightLayer weights = WeightLayerPool.find(to.Id, Id, d);
int width_of_weights = weights.Width, height_of_weights = weights.Height;
for (int y = 0; y < Height; y++)
{
int top = y * stride;
int bottom = top + height_of_weights;
for (int x = 0; x < Width; x++)
{
int left = x * stride;
to.diff_convolute_product(left, top, left + width_of_weights, bottom, Units[x, y, d].gradient_at_inport, weights);
}
}
weights.diff_weights();
}
}
private void backward_fully_connect_on_depth(UnitLayer to, int depth, int length)
{
int to_depth = depth + length;
if (to_depth >= Depth)
{
to_depth = Depth;
}
for (int d = depth; d < to_depth; d++)
{
for (int y = 0; y < Height; y++)
{
for (int x = 0; x < Width; x++)
{
WeightLayer weights = WeightLayerPool.find(to.Id, Id, x, y, d);
to.diff_fully_product(Units[x, y, d].gradient_at_inport, weights);
weights.diff_weights();
}
}
}
}
private void forward_fully_connect_on_depth(UnitLayer to, int depth, int length)
{
int width = to.Width, height = to.Height;
int to_depth = depth + length;
if (to_depth >= to.Depth)
{
to_depth = to.Depth;
}
for (int d = depth; d < to_depth; d++)
{
for (int y = 0; y < height; y++)
{
for (int x = 0; x < width; x++)
{
WeightLayer weights = WeightLayerPool.find(Id, to.Id, x, y, d);
to.set_value_at_inport(x, y, d, weights.fully_product(Units));
}
}
}
}
public void create_convolution(UnitLayer to, int width, int height)
{
WeightLayerPool.create_convolution(this, to, width, height);
}
public void create_fully_connection(UnitLayer to)
{
WeightLayerPool.create_fully_connection(this, to);
}
public void clear_gradients()
{
clear_gradients_of_units();
WeightLayerPool.clear_gradients_of_weights();
}
