How to deal the dataset with the type of " * .tif "?

Hello! I got some troubles with the project since I just wanna to train a generator on my own set of images whose type is " * .tif ". Of course, I appended the code with type of tif in dataset.lua which didn't work. Here is the error message. Hope for solution, Thanks!!! zetn@zetn-All-Series:~/dcgan.torch$ DATA_ROOT=ucm dataset=folder th main.lua{ ntrain : inf beta1 : 0.5 name : "experiment1" niter : 25 batchSize : 64 ndf : 64 fineSize : 64 nz : 100 loadSize : 96 gpu : 1 ngf : 64 dataset : "folder" lr : 0.0002 noise : "normal" nThreads : 4 display_id : 10 display : 1 } Random Seed: 1352
Starting donkey with id: 1 seed: 1353 table: 0x4092fe20 Starting donkey with id: 3 seed: 1355 table: 0x40672f70 Starting donkey with id: 2 seed: 1354 table: 0x40d49b40 Starting donkey with id: 4 seed: 1356 table: 0x40189e20 Creating train metadata table: 0x40a0db68 running "find" on each class directory, and concatenate all those filenames into a single file containing all image paths for a given class now combine all the files to a single large file load the large concatenated list of sample paths to self.imagePath Creating train metadata table: 0x41a1a9a0 running "find" on each class directory, and concatenate all those filenames into a single file containing all image paths for a given class 100 samples found.... 0/100 ....................] ETA: 0ms | Step: 0ms
Updating classList and imageClass appropriately [=================== 1/1 =====================>] Tot: 0ms | Step: 0ms
now combine all the files to a single large file Cleaning up temporary files saved metadata cache at /home/zetn/dcgan.torch/cache/ucm_trainCache.t7 load the large concatenated list of sample paths to self.imagePath 100 samples found.... 0/100 ....................] ETA: 0ms | Step: 0ms
Updating classList and imageClass appropriately [=================== 1/1 =====================>] Tot: 0ms | Step: 0ms
Cleaning up temporary files Loading train metadata from cache saved metadata cache at /home/zetn/dcgan.torch/cache/ucm_trainCache.t7 Loading train metadata from cache Dataset: folder Size: 100 /home/zetn/torch/install/bin/luajit: /home/zetn/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 2 callback] /home/zetn/torch/install/share/lua/5.1/dok/inline.lua:738: unknown image type: tif stack traceback: [C]: in function 'error' /home/zetn/torch/install/share/lua/5.1/dok/inline.lua:738: in function 'error' /home/zetn/torch/install/share/lua/5.1/image/init.lua:392: in function 'load' /home/zetn/dcgan.torch/data/donkey_folder.lua:34: in function 'loadImage' /home/zetn/dcgan.torch/data/donkey_folder.lua:54: in function 'getByClass' /home/zetn/dcgan.torch/data/dataset.lua:341: in function </home/zetn/dcgan.torch/data/dataset.lua:335> [C]: in function 'xpcall' /home/zetn/torch/install/share/lua/5.1/threads/threads.lua:234: in function 'callback' /home/zetn/torch/install/share/lua/5.1/threads/queue.lua:65: in function </home/zetn/torch/install/share/lua/5.1/threads/queue.lua:41> [C]: in function 'pcall' /home/zetn/torch/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob' [string " local Queue = require 'threads.queue'..."]:15: in main chunk stack traceback: [C]: in function 'error' /home/zetn/torch/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob' /home/zetn/dcgan.torch/data/data.lua:85: in function 'getBatch' main.lua:157: in function 'opfunc' /home/zetn/torch/install/share/lua/5.1/optim/adam.lua:37: in function 'adam' main.lua:213: in main chunk [C]: in function 'dofile' ...zetn/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: at 0x00405d50

soumith / dcgan.torch

How to deal the dataset with the type of " * .tif "? #83