--- /dev/null
+
+--[[
+
+ dyncnn is a deep-learning algorithm for the prediction of
+ interacting object dynamics
+
+ Copyright (c) 2016 Idiap Research Institute, http://www.idiap.ch/
+ Written by Francois Fleuret <francois.fleuret@idiap.ch>
+
+ This file is part of dyncnn.
+
+ dyncnn is free software: you can redistribute it and/or modify it
+ under the terms of the GNU General Public License version 3 as
+ published by the Free Software Foundation.
+
+ dyncnn is distributed in the hope that it will be useful, but
+ WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with dyncnn. If not, see <http://www.gnu.org/licenses/>.
+
+]]--
+
+require 'torch'
+
+--[[
+
+The combineImage function takes as input a parameter c which is the
+value to use for the background of the resulting image (padding and
+such), and t which is either a 2d tensor, a 3d tensor, or a table.
+
+ * If t is a 3d tensor, it is returned unchanged.
+
+ * If t is a 2d tensor [r x c], it is reshaped to [1 x r x c] and
+ returned.
+
+ * If t is a table, combineImage first calls itself recursively on
+ t[1], t[2], etc.
+
+ It then creates a new tensor by concatenating the results
+ horizontally if t.vertical is nil, vertically otherwise.
+
+ It adds a padding of t.pad pixels if this field is set.
+
+ * Example
+
+ x = torch.Tensor(64, 64):fill(0.5)
+ y = torch.Tensor(100, 30):fill(0.85)
+
+ i = combineImages(1.0,
+ {
+ pad = 1,
+ vertical = true,
+ { pad = 1, x },
+ {
+ y,
+ { pad = 4, torch.Tensor(32, 16):fill(0.25) },
+ { pad = 1, torch.Tensor(45, 54):uniform(0.25, 0.9) },
+ }
+ }
+ )
+
+ image.save('example.png', i)
+
+]]--
+
+function combineImages(c, t)
+
+ if torch.isTensor(t) then
+
+ if t:dim() == 3 then
+ return t
+ elseif t:dim() == 2 then
+ return torch.Tensor(1, t:size(1), t:size(2)):copy(t)
+ else
+ error('can only deal with [height x width] or [channel x height x width] tensors.')
+ end
+
+ else
+
+ local subImages = {} -- The subimages
+ local nc = 0 -- Nb of columns
+ local nr = 0 -- Nb of rows
+
+ for i, x in ipairs(t) do
+ subImages[i] = combineImages(c, x)
+ if t.vertical then
+ nr = nr + subImages[i]:size(2)
+ nc = math.max(nc, subImages[i]:size(3))
+ else
+ nr = math.max(nr, subImages[i]:size(2))
+ nc = nc + subImages[i]:size(3)
+ end
+ end
+
+ local pad = t.pad or 0
+ local result = torch.Tensor(subImages[1]:size(1), nr + 2 * pad, nc + 2 * pad):fill(c)
+ local co = 1 + pad -- Origin column
+ local ro = 1 + pad -- Origin row
+
+ for i in ipairs(t) do
+
+ result:sub(1, subImages[1]:size(1),
+ ro, ro + subImages[i]:size(2) - 1,
+ co, co + subImages[i]:size(3) - 1):copy(subImages[i])
+
+ if t.vertical then
+ ro = ro + subImages[i]:size(2)
+ else
+ co = co + subImages[i]:size(3)
+ end
+
+ end
+
+ return result
+
+ end
+
+end
+
+--[[
+
+The imageFromTensors function gets as input a list of tensors of
+arbitrary dimensions each, but whose two last dimensions stand for
+height x width. It creates an image tensor (2d, one channel) with each
+argument tensor unfolded per row.
+
+]]--
+
+function imageFromTensors(bt, signed)
+ local gap = 1
+ local tgap = -1
+ local width = 0
+ local height = gap
+
+ for _, t in pairs(bt) do
+ local d = t:dim()
+ local h, w = t:size(d - 1), t:size(d)
+ local n = t:nElement() / (w * h)
+ width = math.max(width, gap + n * (gap + w))
+ height = height + gap + tgap + gap + h
+ end
+
+ local e = torch.Tensor(3, height, width):fill(1.0)
+ local y0 = 1 + gap
+
+ for _, t in pairs(bt) do
+ local d = t:dim()
+ local h, w = t:size(d - 1), t:size(d)
+ local n = t:nElement() / (w * h)
+ local z = t:norm() / math.sqrt(t:nElement())
+
+ local x0 = 1 + gap + math.floor( (width - n * (w + gap)) /2 )
+ local u = torch.Tensor(t:size()):copy(t):resize(n, h, w)
+ for m = 1, n do
+
+ for c = 1, 3 do
+ for y = 0, h+1 do
+ e[c][y0 + y - 1][x0 - 1] = 0.0
+ e[c][y0 + y - 1][x0 + w ] = 0.0
+ end
+ for x = 0, w+1 do
+ e[c][y0 - 1][x0 + x - 1] = 0.0
+ e[c][y0 + h ][x0 + x - 1] = 0.0
+ end
+ end
+
+ for y = 1, h do
+ for x = 1, w do
+ local v = u[m][y][x] / z
+ local r, g, b
+ if signed then
+ if v < -1 then
+ r, g, b = 0.0, 0.0, 1.0
+ elseif v > 1 then
+ r, g, b = 1.0, 0.0, 0.0
+ elseif v >= 0 then
+ r, g, b = 1.0, 1.0 - v, 1.0 - v
+ else
+ r, g, b = 1.0 + v, 1.0 + v, 1.0
+ end
+ else
+ if v <= 0 then
+ r, g, b = 1.0, 1.0, 1.0
+ elseif v > 1 then
+ r, g, b = 0.0, 0.0, 0.0
+ else
+ r, g, b = 1.0 - v, 1.0 - v, 1.0 - v
+ end
+ end
+ e[1][y0 + y - 1][x0 + x - 1] = r
+ e[2][y0 + y - 1][x0 + x - 1] = g
+ e[3][y0 + y - 1][x0 + x - 1] = b
+ end
+ end
+ x0 = x0 + w + gap
+ end
+ y0 = y0 + h + gap + tgap + gap
+ end
+
+ return e
+end
projects / dyncnn.git / blobdiff