fitst commit, support Chinese and min_freq filtering
This commit is contained in:
commit
c874651412
14 files changed
+41232
No files matched your search
@@ -0,0 +1,52 @@
|
||||
|
||||
local GRU = {}
|
||||
|
||||
--[[
|
||||
Creates one timestep of one GRU
|
||||
Paper reference: http://arxiv.org/pdf/1412.3555v1.pdf
|
||||
]]--
|
||||
function GRU.gru(input_size, rnn_size, n)
|
||||
|
||||
-- there are n+1 inputs (hiddens on each layer and x)
|
||||
local inputs = {}
|
||||
table.insert(inputs, nn.Identity()()) -- x
|
||||
for L = 1,n do
|
||||
table.insert(inputs, nn.Identity()()) -- prev_h[L]
|
||||
end
|
||||
|
||||
function new_input_sum(insize, xv, hv)
|
||||
local i2h = nn.Linear(insize, rnn_size)(xv)
|
||||
local h2h = nn.Linear(rnn_size, rnn_size)(hv)
|
||||
return nn.CAddTable()({i2h, h2h})
|
||||
end
|
||||
|
||||
local x, input_size_L
|
||||
local outputs = {}
|
||||
for L = 1,n do
|
||||
|
||||
local prev_h = inputs[L+1]
|
||||
if L == 1 then x = inputs[1] else x = outputs[L-1] end
|
||||
if L == 1 then input_size_L = input_size else input_size_L = rnn_size end
|
||||
|
||||
-- GRU tick
|
||||
-- forward the update and reset gates
|
||||
local update_gate = nn.Sigmoid()(new_input_sum(input_size_L, x, prev_h))
|
||||
local reset_gate = nn.Sigmoid()(new_input_sum(input_size_L, x, prev_h))
|
||||
-- compute candidate hidden state
|
||||
local gated_hidden = nn.CMulTable()({reset_gate, prev_h})
|
||||
local p2 = nn.Linear(rnn_size, rnn_size)(gated_hidden)
|
||||
local p1 = nn.Linear(input_size_L, rnn_size)(x)
|
||||
local hidden_candidate = nn.Tanh()(nn.CAddTable()({p1,p2}))
|
||||
-- compute new interpolated hidden state, based on the update gate
|
||||
local zh = nn.CMulTable()({update_gate, hidden_candidate})
|
||||
local zhm1 = nn.CMulTable()({nn.AddConstant(1,false)(nn.MulConstant(-1,false)(update_gate)), prev_h})
|
||||
local next_h = nn.CAddTable()({zh, zhm1})
|
||||
|
||||
table.insert(outputs, next_h)
|
||||
end
|
||||
|
||||
return nn.gModule(inputs, outputs)
|
||||
end
|
||||
|
||||
return GRU
|
||||
|
||||
@@ -0,0 +1,65 @@
|
||||
|
||||
local LSTM = {}
|
||||
function LSTM.lstm(input_size, rnn_size, n, dropout)
|
||||
dropout = dropout or 0
|
||||
|
||||
-- there will be 2*n+1 inputs
|
||||
local inputs = {}
|
||||
table.insert(inputs, nn.Identity()()) -- x
|
||||
for L = 1,n do
|
||||
table.insert(inputs, nn.Identity()()) -- prev_c[L]
|
||||
table.insert(inputs, nn.Identity()()) -- prev_h[L]
|
||||
end
|
||||
|
||||
local x, input_size_L
|
||||
local outputs = {}
|
||||
for L = 1,n do
|
||||
-- c,h from previos timesteps
|
||||
local prev_h = inputs[L*2+1]
|
||||
local prev_c = inputs[L*2]
|
||||
-- the input to this layer
|
||||
if L == 1 then
|
||||
x = OneHot(input_size)(inputs[1])
|
||||
input_size_L = input_size
|
||||
else
|
||||
x = outputs[(L-1)*2]
|
||||
if dropout > 0 then x = nn.Dropout(dropout)(x) end -- apply dropout, if any
|
||||
input_size_L = rnn_size
|
||||
end
|
||||
-- evaluate the input sums at once for efficiency
|
||||
local i2h = nn.Linear(input_size_L, 4 * rnn_size)(x)
|
||||
local h2h = nn.Linear(rnn_size, 4 * rnn_size)(prev_h)
|
||||
local all_input_sums = nn.CAddTable()({i2h, h2h})
|
||||
-- decode the gates
|
||||
local sigmoid_chunk = nn.Narrow(2, 1, 3 * rnn_size)(all_input_sums)
|
||||
sigmoid_chunk = nn.Sigmoid()(sigmoid_chunk)
|
||||
local in_gate = nn.Narrow(2, 1, rnn_size)(sigmoid_chunk)
|
||||
local forget_gate = nn.Narrow(2, rnn_size + 1, rnn_size)(sigmoid_chunk)
|
||||
local out_gate = nn.Narrow(2, 2 * rnn_size + 1, rnn_size)(sigmoid_chunk)
|
||||
-- decode the write inputs
|
||||
local in_transform = nn.Narrow(2, 3 * rnn_size + 1, rnn_size)(all_input_sums)
|
||||
in_transform = nn.Tanh()(in_transform)
|
||||
-- perform the LSTM update
|
||||
local next_c = nn.CAddTable()({
|
||||
nn.CMulTable()({forget_gate, prev_c}),
|
||||
nn.CMulTable()({in_gate, in_transform})
|
||||
})
|
||||
-- gated cells form the output
|
||||
local next_h = nn.CMulTable()({out_gate, nn.Tanh()(next_c)})
|
||||
|
||||
table.insert(outputs, next_c)
|
||||
table.insert(outputs, next_h)
|
||||
end
|
||||
|
||||
-- set up the decoder
|
||||
local top_h = outputs[#outputs]
|
||||
if dropout > 0 then top_h = nn.Dropout(dropout)(top_h) end
|
||||
local proj = nn.Linear(rnn_size, input_size)(top_h)
|
||||
local logsoft = nn.LogSoftMax()(proj)
|
||||
table.insert(outputs, logsoft)
|
||||
|
||||
return nn.gModule(inputs, outputs)
|
||||
end
|
||||
|
||||
return LSTM
|
||||
|
||||
@@ -0,0 +1,31 @@
|
||||
local RNN = {}
|
||||
|
||||
function RNN.rnn(input_size, rnn_size, n)
|
||||
|
||||
-- there are n+1 inputs (hiddens on each layer and x)
|
||||
local inputs = {}
|
||||
table.insert(inputs, nn.Identity()()) -- x
|
||||
for L = 1,n do
|
||||
table.insert(inputs, nn.Identity()()) -- prev_h[L]
|
||||
end
|
||||
|
||||
local x, input_size_L
|
||||
local outputs = {}
|
||||
for L = 1,n do
|
||||
|
||||
local prev_h = inputs[L+1]
|
||||
if L == 1 then x = inputs[1] else x = outputs[L-1] end
|
||||
if L == 1 then input_size_L = input_size else input_size_L = rnn_size end
|
||||
|
||||
-- RNN tick
|
||||
local i2h = nn.Linear(input_size_L, rnn_size)(x)
|
||||
local h2h = nn.Linear(rnn_size, rnn_size)(prev_h)
|
||||
local next_h = nn.Tanh()(nn.CAddTable(){i2h, h2h})
|
||||
|
||||
table.insert(outputs, next_h)
|
||||
end
|
||||
|
||||
return nn.gModule(inputs, outputs)
|
||||
end
|
||||
|
||||
return RNN
|
||||
Reference in new issue
Block a user