local Dropout = nerv.class("nerv.DropoutLayerT", "nerv.LayerT")

function Dropout:__init(id, global_conf, layer_conf)
    self.id = id
    self.gconf = global_conf
    self.dim_in = layer_conf.dim_in
    self.dim_out = layer_conf.dim_out
    self:check_dim_len(1, 1) -- two inputs: nn output and label
end

function Dropout:init(batch_size, chunk_size)
    if self.dim_in[1] ~= self.dim_out[1] then
        nerv.error("mismatching dimensions of input and output")
    end
    if chunk_size == nil then
        chunk_size = 1
    end
    self.mask_t = {}
    for t = 1, chunk_size do
        self.mask_t[t] = self.gconf.cumat_type(batch_size, self.dim_in[1])
    end
end

function Dropout:batch_resize(batch_size, chunk_size)
    if chunk_size == nil then
        chunk_size = 1
    end
    for t = 1, chunk_size do
        if self.mask_t[t] == nil or self.mask_t[t]:nrow() ~= batch_size then
            self.mask_t[t] = self.gconf.cumat_type(batch_size, self.dim_in[1])
        end
    end
end

function Dropout:propagate(input, output, t)
    if t == nil then
        t = 1
    end
    if self.gconf.dropout_rate == nil then
        nerv.info("DropoutLayerT:propagate warning, global_conf.dropout_rate is nil, setting it zero")
        self.gconf.dropout_rate = 0
    end
    
    if self.gconf.dropout_rate == 0 then
        output[1]:copy_fromd(input[1])
    else
        self.mask_t[t]:rand_uniform()
        --since we will lose a portion of the actvations, we multiply the activations by 1/(1-dr) to compensate
        self.mask_t[t]:thres_mask(self.mask_t[t], self.gconf.dropout_rate, 0, 1 / (1.0 - self.gconf.dropout_rate))
        output[1]:mul_elem(input[1], self.mask_t[t])
    end
end

function Dropout:update(bp_err, input, output, t)
    -- no params, therefore do nothing
end

function Dropout:back_propagate(bp_err, next_bp_err, input, output, t)
    if t == nil then
        t = 1
    end
    if self.gconf.dropout_rate == 0 then
        next_bp_err[1]:copy_fromd(bp_err[1])
    else
        next_bp_err[1]:mul_elem(bp_err[1], self.mask_t[t])
    end
end

function Dropout:get_params()
    return nerv.ParamRepo({})
end