path: root/nerv/nn/network.lua

local network = nerv.class('nerv.Network')

function network:__init(id, global_conf, network_conf)
    self.id = id
    self.dim_in = network_conf.network.dim_in
    self.dim_out = network_conf.network.dim_out
    self.gconf = global_conf
    if self.gconf.use_cpu then
        self.mat_type = self.gconf.mmat_type
    else
        self.mat_type = self.gconf.cumat_type
    end
    self.clip = network_conf.clip
    self.nn_act_default = network_conf.nn_act_default
    if self.nn_act_default == nil then
        self.nn_act_default = 0
    end
    self.layers = {}
    self.input_conn = {}
    self.output_conn = {}
    self.socket = self:compile(network_conf.network)
    for i = 1, #self.dim_in do
        local edge = self.socket.inputs[i]
        local id, port, time = edge[1], edge[2], edge[3]
        if self.input_conn[id][port] ~= nil then
            nerv.error('duplicate edge')
        end
        self.input_conn[id][port] = {0, i, time}
    end
    for i = 1, #self.dim_out do
        local edge = self.socket.outputs[i]
        local id, port, time = edge[1], edge[2], edge[3]
        if self.output_conn[id][port] ~= nil then
            nerv.error('duplicate edge')
        end
        self.output_conn[id][port] = {0, i, time}
    end
    self.delay = 0
    for i = 1, #self.layers do
        local dim_in, _ = self.layers[i]:get_dim()
        for j = 1, #dim_in do
            local time = self.input_conn[i][j][3]
            if math.abs(time) > self.delay then
                self.delay = math.abs(time)
            end
        end
    end
end

function network:compile(layer)
    local socket = {inputs = {}, outputs = {}}
    if not nerv.is_type(layer, 'nerv.GraphLayer') then
        table.insert(self.layers, layer)
        local id = #self.layers
        self.input_conn[id] = {}
        self.output_conn[id] = {}
        local dim_in, dim_out = layer:get_dim()
        for i = 1, #dim_in do
            socket.inputs[i] = {id, i, 0}
        end
        for i = 1, #dim_out do
            socket.outputs[i] = {id, i, 0}
        end
    else
        local sublayer_socket = {}
        for id, sublayer in pairs(layer.layers) do
            if id ~= '<input>' then
               sublayer_socket[sublayer.id] = self:compile(sublayer.layer)
            end
        end
        for _, edge in pairs(layer.connections) do
            -- id = 0 means <input> or <output>
            local id_from, port_from = edge[1], edge[2]
            local id_to, port_to = edge[3], edge[4]
            local time = edge[5]
            if id_from == 0 then
                if socket.inputs[port_from] ~= nil then
                    nerv.error('duplicate input socket')
                end
                local input = sublayer_socket[id_to].inputs[port_to]
                local id, port, t = input[1], input[2], input[3] + time
                socket.inputs[port_from] = {id, port, t}
            else
                local output = sublayer_socket[id_from].outputs[port_from]
                local id, port, t = output[1], output[2], output[3] + time
                if id_to == 0 then
                    if socket.outputs[port_to] ~= nil then
                        nerv.error('duplicate output socket')
                    end
                    socket.outputs[port_to] = {id, port, t}
                else
                    local input = sublayer_socket[id_to].inputs[port_to]
                    local id1, port1, t1 = input[1], input[2], input[3]
                    if self.input_conn[id1][port1] ~= nil or self.output_conn[id][port] ~= nil then
                        nerv.error('duplicate edge')
                    end
                    self.input_conn[id1][port1] = {id, port, t + t1}
                    self.output_conn[id][port] = {id1, port1, t + t1}
                end
            end
        end
    end
    return socket
end

function network:init(batch_size, chunk_size)
    self.batch_size = batch_size
    self.chunk_size = chunk_size

    self:topsort()
    
    self:make_initial_store()
    collectgarbage('collect')
end

function network:topsort()
    nerv.info('Network topology sort')
    local degree = {}
    for t = 1, self.chunk_size do
        degree[t] = {}
        for i = 1, #self.layers do  
            degree[t][i] = 0
        end
    end

    for t = 1, self.chunk_size do
        for i = 1, #self.layers do
            local _, dim_out = self.layers[i]:get_dim()
            for j = 1, #dim_out do
                if self.output_conn[i][j] ~= nil then
                    local edge = self.output_conn[i][j]
                    local id, _, time = edge[1], edge[2], edge[3] + t
                    if time >= 1 and time <= self.chunk_size and id ~= 0 then
                        degree[time][id] = degree[time][id] + 1
                    end
                end
            end
        end
    end

    self.queue = {}
    local l = 1
    local r = 0
    for t = 1, self.chunk_size do
        for i = 1, #self.layers do
            if degree[t][i] == 0 then
                r = r + 1
                self.queue[r] = {chunk = t, id = i}
            end
        end
    end
    while l<=r do
        local t, i = self.queue[l].chunk, self.queue[l].id
        l = l + 1
        local _, dim_out = self.layers[i]:get_dim()
        for j = 1, #dim_out do
            if self.output_conn[i][j] ~= nil then
                local edge = self.output_conn[i][j]
                local id, _, time = edge[1], edge[2], edge[3] + t
                if time >= 1 and time <= self.chunk_size and id ~= 0 then
                    degree[time][id] = degree[time][id] - 1
                    if degree[time][id] == 0 then
                        r = r + 1
                        self.queue[r] = {chunk = time, id = id}
                    end
                end
            end
        end
    end

    if r ~= self.chunk_size * #self.layers then
        nerv.error('loop detected')
    end
end

function network:make_initial_store()
    nerv.info('Network initing storage')

    -- allocate memory
    local memory = {}
    local err_memory = {}
    for t = 1 - self.delay, self.chunk_size + self.delay do
        memory[t] = {}
        err_memory[t] = {}
        for i = 1, #self.layers do
            memory[t][i] = {}
            err_memory[t][i] = {}
            local dim_in, dim_out = self.layers[i]:get_dim()
            for j = 1, #dim_in do
                err_memory[t][i][j] = self.mat_type(self.batch_size, dim_in[j])
                err_memory[t][i][j]:fill(0)
            end
            for j = 1, #dim_out do
                memory[t][i][j] = self.mat_type(self.batch_size, dim_out[j])
                memory[t][i][j]:fill(self.nn_act_default)
            end
        end
        -- memory[t][0] stores network input
        memory[t][0] = {}
        for j = 1, #self.dim_in do
            memory[t][0][j] = self.mat_type(self.batch_size, self.dim_in[j])
            memory[t][0][j]:fill(self.nn_act_default)
        end
        -- err_memory[t][0] stores network err_input
        err_memory[t][0] = {}
        for j = 1, #self.dim_out do
            err_memory[t][0][j] = self.mat_type(self.batch_size, self.dim_out[j])
            err_memory[t][0][j]:fill(0)
        end
    end

    -- connect memory and reference 
    self.input = {}
    self.output = {}
    self.err_input = {}
    self.err_output = {}
    for t = 1, self.chunk_size do
        self.input[t] = {}
        self.output[t] = {}
        self.err_input[t] = {}
        self.err_output[t] = {}
        for i = 1, #self.layers do
            self.input[t][i] = {}
            self.output[t][i] = {}
            self.err_input[t][i] = {}
            self.err_output[t][i] = {}
            local dim_in, dim_out = self.layers[i]:get_dim()
            for j = 1, #dim_in do
                local edge = self.input_conn[i][j]
                local id, port, time = edge[1], edge[2], edge[3]
                if id ~= 0 or t - time < 1 or t - time > self.chunk_size then
                    self.input[t][i][j] = memory[t - time][id][port]
                end
                if id ~= 0 then