rhgao/on-demand-learning

On-Demand Learning for Deep Image Restoration (ICCV 2017)

on-demand-learning's Issues

how to calculate PSNR for training my own dataset?

thanks for sharing your work.
i trained my dataset for inpainting but only L2 loss is computed while training how to also calculate PSNR while training?
thanks

local data = DataLoader.new(opt.nThreads, opt) demo.lua error

Starting donkey with id: 1 seed: 334
table: 0x16a75dd0
Creating train metadata
table: 0x16af0f60
running "find" on each class directory, and concatenate all those filenames into a single file containing all image paths for a given class
/tmp/lua_w3KL36: line 1: gfind: command not found
now combine all the files to a single large file
load the large concatenated list of sample paths to self.imagePath
/Users/anthonyyuan/torch/install/bin/luajit: ...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 1 callback] ...mand-learning-master/pixelInterpolation/data/dataset.lua:202: Could not find any image file in the given input paths
stack traceback:
[C]: in function 'assert'
...mand-learning-master/pixelInterpolation/data/dataset.lua:202: in function '__init'
...s/anthonyyuan/torch/install/share/lua/5.1/torch/init.lua:91: in function <...s/anthonyyuan/torch/install/share/lua/5.1/torch/init.lua:87>
[C]: in function 'dataLoader'
...earning-master/pixelInterpolation/data/donkey_folder.lua:99: in main chunk
[C]: in function 'dofile'
...-demand-learning-master/pixelInterpolation/data/data.lua:38: in function <...-demand-learning-master/pixelInterpolation/data/data.lua:28>
[C]: in function 'xpcall'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:234: in function 'callback'
...nthonyyuan/torch/install/share/lua/5.1/threads/queue.lua:65: in function <...nthonyyuan/torch/install/share/lua/5.1/threads/queue.lua:41>
[C]: in function 'pcall'
...nthonyyuan/torch/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob'
[string " local Queue = require 'threads.queue'..."]:13: in main chunk
stack traceback:
[C]: in function 'error'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:264: in function 'synchronize'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:142: in function 'specific'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:125: in function 'Threads'
...-demand-learning-master/pixelInterpolation/data/data.lua:26: in function 'new'
demo.lua:63: in main chunk
[C]: in function 'dofile'
...yuan/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x0107e58bc0

Hoping for

Sorry if this is too much of a newb question, but...

I'm really hoping for step-by-step instructions on how to get this working on win-7?

I would love to play with this, but I have never used this language before and am only a programming hobbyists (mostly in c#).

I'm sure if you included an easy way to install this more people would use i

Can u tell me how to do my database?

Can u tell me how to do my database?

Can I train 256 - size data

/Users/anthonyyuan/torch/install/bin/luajit: ...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 1 callback] ...earning-master/pixelInterpolation/data/donkey_folder.lua:24: bad argument #2 to 'error' (number expected, got string) stack traceback:

DATA_ROOT=../dataset/my_test_set name=pixelInter_demo net=../models/pixelInterpolation_net_G.t7 manualSeed=333 gpu=1 display=1 th demo.lua
{
gpu : 1
nc : 3
name : "pixelInter_demo"
batchSize : 100
net : "../models/pixelInterpolation_net_G.t7"
fineSize : 64
manualSeed : 333
nThreads : 1
display : 1
loadSize : 96
}
Seed: 333
Using CUDNN !
nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> (11) -> (12) -> (13) -> (14) -> output]
(1): nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> (11) -> (12) -> output]
(1): cudnn.SpatialConvolution(3 -> 64, 4x4, 2,2, 1,1)
(2): nn.SpatialBatchNormalization (4D) (64)
(3): nn.LeakyReLU(0.2)
(4): cudnn.SpatialConvolution(64 -> 128, 4x4, 2,2, 1,1)
(5): nn.SpatialBatchNormalization (4D) (128)
(6): nn.LeakyReLU(0.2)
(7): cudnn.SpatialConvolution(128 -> 256, 4x4, 2,2, 1,1)
(8): nn.SpatialBatchNormalization (4D) (256)
(9): nn.LeakyReLU(0.2)
(10): cudnn.SpatialConvolution(256 -> 512, 4x4, 2,2, 1,1)
(11): nn.SpatialBatchNormalization (4D) (512)
(12): nn.LeakyReLU(0.2)
}
(2): nn.Sequential {
[input -> (1) -> (2) -> (3) -> (4) -> output]
(1): nn.View(512, 16)
(2): nn.SplitTable
(3): nn.ParallelTable {
input
|-> (1): nn.Linear(16 -> 16) |-> (2): nn.Linear(16 -> 16)
|-> (3): nn.Linear(16 -> 16) |-> (4): nn.Linear(16 -> 16)
|-> (5): nn.Linear(16 -> 16) |-> (6): nn.Linear(16 -> 16)
|-> (7): nn.Linear(16 -> 16) |-> (8): nn.Linear(16 -> 16)
|-> (9): nn.Linear(16 -> 16) |-> (10): nn.Linear(16 -> 16)
|-> (11): nn.Linear(16 -> 16) |-> (12): nn.Linear(16 -> 16)
|-> (13): nn.Linear(16 -> 16) |-> (14): nn.Linear(16 -> 16)
|-> (15): nn.Linear(16 -> 16) |-> (16): nn.Linear(16 -> 16)
|-> (17): nn.Linear(16 -> 16) |-> (18): nn.Linear(16 -> 16)
|-> (19): nn.Linear(16 -> 16) |-> (20): nn.Linear(16 -> 16)
|-> (21): nn.Linear(16 -> 16) |-> (22): nn.Linear(16 -> 16)
|-> (23): nn.Linear(16 -> 16) |-> (24): nn.Linear(16 -> 16)
|-> (25): nn.Linear(16 -> 16) |-> (26): nn.Linear(16 -> 16)
|-> (27): nn.Linear(16 -> 16) |-> (28): nn.Linear(16 -> 16)
|-> (29): nn.Linear(16 -> 16) |-> (30): nn.Linear(16 -> 16)
|-> (31): nn.Linear(16 -> 16) |-> (32): nn.Linear(16 -> 16)
|-> (33): nn.Linear(16 -> 16) |-> (34): nn.Linear(16 -> 16)
|-> (35): nn.Linear(16 -> 16) |-> (36): nn.Linear(16 -> 16)
|-> (37): nn.Linear(16 -> 16) |-> (38): nn.Linear(16 -> 16)
|-> (39): nn.Linear(16 -> 16) |-> (40): nn.Linear(16 -> 16)
|-> (41): nn.Linear(16 -> 16) |-> (42): nn.Linear(16 -> 16)
|-> (43): nn.Linear(16 -> 16) |-> (44): nn.Linear(16 -> 16)
|-> (45): nn.Linear(16 -> 16) |-> (46): nn.Linear(16 -> 16)
|-> (47): nn.Linear(16 -> 16) |-> (48): nn.Linear(16 -> 16)
|-> (49): nn.Linear(16 -> 16) |-> (50): nn.Linear(16 -> 16)
|-> (51): nn.Linear(16 -> 16) |-> (52): nn.Linear(16 -> 16)
|-> (53): nn.Linear(16 -> 16) |-> (54): nn.Linear(16 -> 16)
|-> (55): nn.Linear(16 -> 16) |-> (56): nn.Linear(16 -> 16)
|-> (57): nn.Linear(16 -> 16) |-> (58): nn.Linear(16 -> 16)
|-> (59): nn.Linear(16 -> 16) |-> (60): nn.Linear(16 -> 16)
|-> (61): nn.Linear(16 -> 16) |-> (62): nn.Linear(16 -> 16)
|-> (63): nn.Linear(16 -> 16) |-> (64): nn.Linear(16 -> 16)
|-> (65): nn.Linear(16 -> 16) |-> (66): nn.Linear(16 -> 16)
|-> (67): nn.Linear(16 -> 16) |-> (68): nn.Linear(16 -> 16)
|-> (69): nn.Linear(16 -> 16) |-> (70): nn.Linear(16 -> 16)
|-> (71): nn.Linear(16 -> 16) |-> (72): nn.Linear(16 -> 16)
|-> (73): nn.Linear(16 -> 16) |-> (74): nn.Linear(16 -> 16)
|-> (75): nn.Linear(16 -> 16) |-> (76): nn.Linear(16 -> 16)
|-> (77): nn.Linear(16 -> 16) |-> (78): nn.Linear(16 -> 16)
|-> (79): nn.Linear(16 -> 16) |-> (80): nn.Linear(16 -> 16)
|-> (81): nn.Linear(16 -> 16) |-> (82): nn.Linear(16 -> 16)
|-> (83): nn.Linear(16 -> 16) |-> (84): nn.Linear(16 -> 16)
|-> (85): nn.Linear(16 -> 16) |-> (86): nn.Linear(16 -> 16)
|-> (87): nn.Linear(16 -> 16) |-> (88): nn.Linear(16 -> 16)
|-> (89): nn.Linear(16 -> 16) |-> (90): nn.Linear(16 -> 16)
|-> (91): nn.Linear(16 -> 16) |-> (92): nn.Linear(16 -> 16)
|-> (93): nn.Linear(16 -> 16) |-> (94): nn.Linear(16 -> 16)
|-> (95): nn.Linear(16 -> 16) |-> (96): nn.Linear(16 -> 16)
|-> (97): nn.Linear(16 -> 16) |-> (98): nn.Linear(16 -> 16)
|-> (99): nn.Linear(16 -> 16) |-> (100): nn.Linear(16 -> 16)
|-> (101): nn.Linear(16 -> 16) |-> (102): nn.Linear(16 -> 16)
|-> (103): nn.Linear(16 -> 16) |-> (104): nn.Linear(16 -> 16)
|-> (105): nn.Linear(16 -> 16) |-> (106): nn.Linear(16 -> 16)
|-> (107): nn.Linear(16 -> 16) |-> (108): nn.Linear(16 -> 16)
|-> (109): nn.Linear(16 -> 16) |-> (110): nn.Linear(16 -> 16)
|-> (111): nn.Linear(16 -> 16) |-> (112): nn.Linear(16 -> 16)
|-> (113): nn.Linear(16 -> 16) |-> (114): nn.Linear(16 -> 16)
|-> (115): nn.Linear(16 -> 16) |-> (116): nn.Linear(16 -> 16)
|-> (117): nn.Linear(16 -> 16) |-> (118): nn.Linear(16 -> 16)
|-> (119): nn.Linear(16 -> 16) |-> (120): nn.Linear(16 -> 16)
|-> (121): nn.Linear(16 -> 16) |-> (122): nn.Linear(16 -> 16)
|-> (123): nn.Linear(16 -> 16) |-> (124): nn.Linear(16 -> 16)
|-> (125): nn.Linear(16 -> 16) |-> (126): nn.Linear(16 -> 16)
|-> (127): nn.Linear(16 -> 16) |-> (128): nn.Linear(16 -> 16)
|-> (129): nn.Linear(16 -> 16) |-> (130): nn.Linear(16 -> 16)
|-> (131): nn.Linear(16 -> 16) |-> (132): nn.Linear(16 -> 16)
|-> (133): nn.Linear(16 -> 16) |-> (134): nn.Linear(16 -> 16)
|-> (135): nn.Linear(16 -> 16) |-> (136): nn.Linear(16 -> 16)
|-> (137): nn.Linear(16 -> 16) |-> (138): nn.Linear(16 -> 16)
|-> (139): nn.Linear(16 -> 16) |-> (140): nn.Linear(16 -> 16)
|-> (141): nn.Linear(16 -> 16) |-> (142): nn.Linear(16 -> 16)
|-> (143): nn.Linear(16 -> 16) |-> (144): nn.Linear(16 -> 16)
|-> (145): nn.Linear(16 -> 16) |-> (146): nn.Linear(16 -> 16)
|-> (147): nn.Linear(16 -> 16) |-> (148): nn.Linear(16 -> 16)
|-> (149): nn.Linear(16 -> 16) |-> (150): nn.Linear(16 -> 16)
|-> (151): nn.Linear(16 -> 16) |-> (152): nn.Linear(16 -> 16)
|-> (153): nn.Linear(16 -> 16) |-> (154): nn.Linear(16 -> 16)
|-> (155): nn.Linear(16 -> 16) |-> (156): nn.Linear(16 -> 16)
|-> (157): nn.Linear(16 -> 16) |-> (158): nn.Linear(16 -> 16)
|-> (159): nn.Linear(16 -> 16) |-> (160): nn.Linear(16 -> 16)
|-> (161): nn.Linear(16 -> 16) |-> (162): nn.Linear(16 -> 16)
|-> (163): nn.Linear(16 -> 16) |-> (164): nn.Linear(16 -> 16)
|-> (165): nn.Linear(16 -> 16) |-> (166): nn.Linear(16 -> 16)
|-> (167): nn.Linear(16 -> 16) |-> (168): nn.Linear(16 -> 16)
|-> (169): nn.Linear(16 -> 16) |-> (170): nn.Linear(16 -> 16)
|-> (171): nn.Linear(16 -> 16) |-> (172): nn.Linear(16 -> 16)
|-> (173): nn.Linear(16 -> 16) |-> (174): nn.Linear(16 -> 16)
|-> (175): nn.Linear(16 -> 16) |-> (176): nn.Linear(16 -> 16)
|-> (177): nn.Linear(16 -> 16) |-> (178): nn.Linear(16 -> 16)
|-> (179): nn.Linear(16 -> 16) |-> (180): nn.Linear(16 -> 16)
|-> (181): nn.Linear(16 -> 16) |-> (182): nn.Linear(16 -> 16)
|-> (183): nn.Linear(16 -> 16) |-> (184): nn.Linear(16 -> 16)
|-> (185): nn.Linear(16 -> 16) |-> (186): nn.Linear(16 -> 16)
|-> (187): nn.Linear(16 -> 16) |-> (188): nn.Linear(16 -> 16)
|-> (189): nn.Linear(16 -> 16) |-> (190): nn.Linear(16 -> 16)
|-> (191): nn.Linear(16 -> 16) |-> (192): nn.Linear(16 -> 16)
|-> (193): nn.Linear(16 -> 16) |-> (194): nn.Linear(16 -> 16)
|-> (195): nn.Linear(16 -> 16) |-> (196): nn.Linear(16 -> 16)
|-> (197): nn.Linear(16 -> 16) |-> (198): nn.Linear(16 -> 16)
|-> (199): nn.Linear(16 -> 16) |-> (200): nn.Linear(16 -> 16)
|-> (201): nn.Linear(16 -> 16) |-> (202): nn.Linear(16 -> 16)
|-> (203): nn.Linear(16 -> 16) |-> (204): nn.Linear(16 -> 16)
|-> (205): nn.Linear(16 -> 16) |-> (206): nn.Linear(16 -> 16)
|-> (207): nn.Linear(16 -> 16) |-> (208): nn.Linear(16 -> 16)
|-> (209): nn.Linear(16 -> 16) |-> (210): nn.Linear(16 -> 16)
|-> (211): nn.Linear(16 -> 16) |-> (212): nn.Linear(16 -> 16)
|-> (213): nn.Linear(16 -> 16) |-> (214): nn.Linear(16 -> 16)
|-> (215): nn.Linear(16 -> 16) |-> (216): nn.Linear(16 -> 16)
|-> (217): nn.Linear(16 -> 16) |-> (218): nn.Linear(16 -> 16)
|-> (219): nn.Linear(16 -> 16) |-> (220): nn.Linear(16 -> 16)
|-> (221): nn.Linear(16 -> 16) |-> (222): nn.Linear(16 -> 16)
|-> (223): nn.Linear(16 -> 16) |-> (224): nn.Linear(16 -> 16)
|-> (225): nn.Linear(16 -> 16) |-> (226): nn.Linear(16 -> 16)
|-> (227): nn.Linear(16 -> 16) |-> (228): nn.Linear(16 -> 16)
|-> (229): nn.Linear(16 -> 16) |-> (230): nn.Linear(16 -> 16)
|-> (231): nn.Linear(16 -> 16) |-> (232): nn.Linear(16 -> 16)
|-> (233): nn.Linear(16 -> 16) |-> (234): nn.Linear(16 -> 16)
|-> (235): nn.Linear(16 -> 16) |-> (236): nn.Linear(16 -> 16)
|-> (237): nn.Linear(16 -> 16) |-> (238): nn.Linear(16 -> 16)
|-> (239): nn.Linear(16 -> 16) |-> (240): nn.Linear(16 -> 16)
|-> (241): nn.Linear(16 -> 16) |-> (242): nn.Linear(16 -> 16)
|-> (243): nn.Linear(16 -> 16) |-> (244): nn.Linear(16 -> 16)
|-> (245): nn.Linear(16 -> 16) |-> (246): nn.Linear(16 -> 16)
|-> (247): nn.Linear(16 -> 16) |-> (248): nn.Linear(16 -> 16)
|-> (249): nn.Linear(16 -> 16) |-> (250): nn.Linear(16 -> 16)
|-> (251): nn.Linear(16 -> 16) |-> (252): nn.Linear(16 -> 16)
|-> (253): nn.Linear(16 -> 16) |-> (254): nn.Linear(16 -> 16)
|-> (255): nn.Linear(16 -> 16) |-> (256): nn.Linear(16 -> 16)
|-> (257): nn.Linear(16 -> 16) |-> (258): nn.Linear(16 -> 16)
|-> (259): nn.Linear(16 -> 16) |-> (260): nn.Linear(16 -> 16)
|-> (261): nn.Linear(16 -> 16) |-> (262): nn.Linear(16 -> 16)
|-> (263): nn.Linear(16 -> 16) |-> (264): nn.Linear(16 -> 16)
|-> (265): nn.Linear(16 -> 16) |-> (266): nn.Linear(16 -> 16)
|-> (267): nn.Linear(16 -> 16) |-> (268): nn.Linear(16 -> 16)
|-> (269): nn.Linear(16 -> 16) |-> (270): nn.Linear(16 -> 16)
|-> (271): nn.Linear(16 -> 16) |-> (272): nn.Linear(16 -> 16)
|-> (273): nn.Linear(16 -> 16) |-> (274): nn.Linear(16 -> 16)
|-> (275): nn.Linear(16 -> 16) |-> (276): nn.Linear(16 -> 16)
|-> (277): nn.Linear(16 -> 16) |-> (278): nn.Linear(16 -> 16)
|-> (279): nn.Linear(16 -> 16) |-> (280): nn.Linear(16 -> 16)
|-> (281): nn.Linear(16 -> 16) |-> (282): nn.Linear(16 -> 16)
|-> (283): nn.Linear(16 -> 16) |-> (284): nn.Linear(16 -> 16)
|-> (285): nn.Linear(16 -> 16) |-> (286): nn.Linear(16 -> 16)
|-> (287): nn.Linear(16 -> 16) |-> (288): nn.Linear(16 -> 16)
|-> (289): nn.Linear(16 -> 16) |-> (290): nn.Linear(16 -> 16)
|-> (291): nn.Linear(16 -> 16) |-> (292): nn.Linear(16 -> 16)
|-> (293): nn.Linear(16 -> 16) |-> (294): nn.Linear(16 -> 16)
|-> (295): nn.Linear(16 -> 16) |-> (296): nn.Linear(16 -> 16)
|-> (297): nn.Linear(16 -> 16) |-> (298): nn.Linear(16 -> 16)
|-> (299): nn.Linear(16 -> 16) |-> (300): nn.Linear(16 -> 16)
|-> (301): nn.Linear(16 -> 16) |-> (302): nn.Linear(16 -> 16)
|-> (303): nn.Linear(16 -> 16) |-> (304): nn.Linear(16 -> 16)
|-> (305): nn.Linear(16 -> 16) |-> (306): nn.Linear(16 -> 16)
|-> (307): nn.Linear(16 -> 16) |-> (308): nn.Linear(16 -> 16)
|-> (309): nn.Linear(16 -> 16) |-> (310): nn.Linear(16 -> 16)
|-> (311): nn.Linear(16 -> 16) |-> (312): nn.Linear(16 -> 16)
|-> (313): nn.Linear(16 -> 16) |-> (314): nn.Linear(16 -> 16)
|-> (315): nn.Linear(16 -> 16) |-> (316): nn.Linear(16 -> 16)
|-> (317): nn.Linear(16 -> 16) |-> (318): nn.Linear(16 -> 16)
|-> (319): nn.Linear(16 -> 16) |-> (320): nn.Linear(16 -> 16)
|-> (321): nn.Linear(16 -> 16) |-> (322): nn.Linear(16 -> 16)
|-> (323): nn.Linear(16 -> 16) |-> (324): nn.Linear(16 -> 16)
|-> (325): nn.Linear(16 -> 16) |-> (326): nn.Linear(16 -> 16)
|-> (327): nn.Linear(16 -> 16) |-> (328): nn.Linear(16 -> 16)
|-> (329): nn.Linear(16 -> 16) |-> (330): nn.Linear(16 -> 16)
|-> (331): nn.Linear(16 -> 16) |-> (332): nn.Linear(16 -> 16)
|-> (333): nn.Linear(16 -> 16) |-> (334): nn.Linear(16 -> 16)
|-> (335): nn.Linear(16 -> 16) |-> (336): nn.Linear(16 -> 16)
|-> (337): nn.Linear(16 -> 16) |-> (338): nn.Linear(16 -> 16)
|-> (339): nn.Linear(16 -> 16) |-> (340): nn.Linear(16 -> 16)
|-> (341): nn.Linear(16 -> 16) |-> (342): nn.Linear(16 -> 16)
|-> (343): nn.Linear(16 -> 16) |-> (344): nn.Linear(16 -> 16)
|-> (345): nn.Linear(16 -> 16) |-> (346): nn.Linear(16 -> 16)
|-> (347): nn.Linear(16 -> 16) |-> (348): nn.Linear(16 -> 16)
|-> (349): nn.Linear(16 -> 16) |-> (350): nn.Linear(16 -> 16)
|-> (351): nn.Linear(16 -> 16) |-> (352): nn.Linear(16 -> 16)
|-> (353): nn.Linear(16 -> 16) |-> (354): nn.Linear(16 -> 16)
|-> (355): nn.Linear(16 -> 16) |-> (356): nn.Linear(16 -> 16)
|-> (357): nn.Linear(16 -> 16) |-> (358): nn.Linear(16 -> 16)
|-> (359): nn.Linear(16 -> 16) |-> (360): nn.Linear(16 -> 16)
|-> (361): nn.Linear(16 -> 16) |-> (362): nn.Linear(16 -> 16)
|-> (363): nn.Linear(16 -> 16) |-> (364): nn.Linear(16 -> 16)
|-> (365): nn.Linear(16 -> 16) |-> (366): nn.Linear(16 -> 16)
|-> (367): nn.Linear(16 -> 16) |-> (368): nn.Linear(16 -> 16)
|-> (369): nn.Linear(16 -> 16) |-> (370): nn.Linear(16 -> 16)
|-> (371): nn.Linear(16 -> 16) |-> (372): nn.Linear(16 -> 16)
|-> (373): nn.Linear(16 -> 16) |-> (374): nn.Linear(16 -> 16)
|-> (375): nn.Linear(16 -> 16) |-> (376): nn.Linear(16 -> 16)
|-> (377): nn.Linear(16 -> 16) |-> (378): nn.Linear(16 -> 16)
|-> (379): nn.Linear(16 -> 16) |-> (380): nn.Linear(16 -> 16)
|-> (381): nn.Linear(16 -> 16) |-> (382): nn.Linear(16 -> 16)
|-> (383): nn.Linear(16 -> 16) |-> (384): nn.Linear(16 -> 16)
|-> (385): nn.Linear(16 -> 16) |-> (386): nn.Linear(16 -> 16)
|-> (387): nn.Linear(16 -> 16) |-> (388): nn.Linear(16 -> 16)
|-> (389): nn.Linear(16 -> 16) |-> (390): nn.Linear(16 -> 16)
|-> (391): nn.Linear(16 -> 16) |-> (392): nn.Linear(16 -> 16)
|-> (393): nn.Linear(16 -> 16) |-> (394): nn.Linear(16 -> 16)
|-> (395): nn.Linear(16 -> 16) |-> (396): nn.Linear(16 -> 16)
|-> (397): nn.Linear(16 -> 16) |-> (398): nn.Linear(16 -> 16)
|-> (399): nn.Linear(16 -> 16) |-> (400): nn.Linear(16 -> 16)
|-> (401): nn.Linear(16 -> 16) |-> (402): nn.Linear(16 -> 16)
|-> (403): nn.Linear(16 -> 16) |-> (404): nn.Linear(16 -> 16)
|-> (405): nn.Linear(16 -> 16) |-> (406): nn.Linear(16 -> 16)
|-> (407): nn.Linear(16 -> 16) |-> (408): nn.Linear(16 -> 16)
|-> (409): nn.Linear(16 -> 16) |-> (410): nn.Linear(16 -> 16)
|-> (411): nn.Linear(16 -> 16) |-> (412): nn.Linear(16 -> 16)
|-> (413): nn.Linear(16 -> 16) |-> (414): nn.Linear(16 -> 16)
|-> (415): nn.Linear(16 -> 16) |-> (416): nn.Linear(16 -> 16)
|-> (417): nn.Linear(16 -> 16) |-> (418): nn.Linear(16 -> 16)
|-> (419): nn.Linear(16 -> 16) |-> (420): nn.Linear(16 -> 16)
|-> (421): nn.Linear(16 -> 16) |-> (422): nn.Linear(16 -> 16)
|-> (423): nn.Linear(16 -> 16) |-> (424): nn.Linear(16 -> 16)
|-> (425): nn.Linear(16 -> 16) |-> (426): nn.Linear(16 -> 16)
|-> (427): nn.Linear(16 -> 16) |-> (428): nn.Linear(16 -> 16)
|-> (429): nn.Linear(16 -> 16) |-> (430): nn.Linear(16 -> 16)
|-> (431): nn.Linear(16 -> 16) |-> (432): nn.Linear(16 -> 16)
|-> (433): nn.Linear(16 -> 16) |-> (434): nn.Linear(16 -> 16)
|-> (435): nn.Linear(16 -> 16) |-> (436): nn.Linear(16 -> 16)
|-> (437): nn.Linear(16 -> 16) |-> (438): nn.Linear(16 -> 16)
|-> (439): nn.Linear(16 -> 16) |-> (440): nn.Linear(16 -> 16)
|-> (441): nn.Linear(16 -> 16) |-> (442): nn.Linear(16 -> 16)
|-> (443): nn.Linear(16 -> 16) |-> (444): nn.Linear(16 -> 16)
|-> (445): nn.Linear(16 -> 16) |-> (446): nn.Linear(16 -> 16)
|-> (447): nn.Linear(16 -> 16) |-> (448): nn.Linear(16 -> 16)
|-> (449): nn.Linear(16 -> 16) |-> (450): nn.Linear(16 -> 16)
|-> (451): nn.Linear(16 -> 16) |-> (452): nn.Linear(16 -> 16)
|-> (453): nn.Linear(16 -> 16) |-> (454): nn.Linear(16 -> 16)
|-> (455): nn.Linear(16 -> 16) |-> (456): nn.Linear(16 -> 16)
|-> (457): nn.Linear(16 -> 16) |-> (458): nn.Linear(16 -> 16)
|-> (459): nn.Linear(16 -> 16) |-> (460): nn.Linear(16 -> 16)
|-> (461): nn.Linear(16 -> 16) |-> (462): nn.Linear(16 -> 16)
|-> (463): nn.Linear(16 -> 16) |-> (464): nn.Linear(16 -> 16)
|-> (465): nn.Linear(16 -> 16) |-> (466): nn.Linear(16 -> 16)
|-> (467): nn.Linear(16 -> 16) |-> (468): nn.Linear(16 -> 16)
|-> (469): nn.Linear(16 -> 16) |-> (470): nn.Linear(16 -> 16)
|-> (471): nn.Linear(16 -> 16) |-> (472): nn.Linear(16 -> 16)
|-> (473): nn.Linear(16 -> 16) |-> (474): nn.Linear(16 -> 16)
|-> (475): nn.Linear(16 -> 16) |-> (476): nn.Linear(16 -> 16)
|-> (477): nn.Linear(16 -> 16) |-> (478): nn.Linear(16 -> 16)
|-> (479): nn.Linear(16 -> 16) |-> (480): nn.Linear(16 -> 16)
|-> (481): nn.Linear(16 -> 16) |-> (482): nn.Linear(16 -> 16)
|-> (483): nn.Linear(16 -> 16) |-> (484): nn.Linear(16 -> 16)
|-> (485): nn.Linear(16 -> 16) |-> (486): nn.Linear(16 -> 16)
|-> (487): nn.Linear(16 -> 16) |-> (488): nn.Linear(16 -> 16)
|-> (489): nn.Linear(16 -> 16) |-> (490): nn.Linear(16 -> 16)
|-> (491): nn.Linear(16 -> 16) |-> (492): nn.Linear(16 -> 16)
|-> (493): nn.Linear(16 -> 16) |-> (494): nn.Linear(16 -> 16)
|-> (495): nn.Linear(16 -> 16) |-> (496): nn.Linear(16 -> 16)
|-> (497): nn.Linear(16 -> 16) |-> (498): nn.Linear(16 -> 16)
|-> (499): nn.Linear(16 -> 16) |-> (500): nn.Linear(16 -> 16)
|-> (501): nn.Linear(16 -> 16) |-> (502): nn.Linear(16 -> 16)
|-> (503): nn.Linear(16 -> 16) |-> (504): nn.Linear(16 -> 16)
|-> (505): nn.Linear(16 -> 16) |-> (506): nn.Linear(16 -> 16)
|-> (507): nn.Linear(16 -> 16) |-> (508): nn.Linear(16 -> 16)
|-> (509): nn.Linear(16 -> 16) |-> (510): nn.Linear(16 -> 16)
|-> (511): nn.Linear(16 -> 16) -> (512): nn.Linear(16 -> 16)
... -> output
}
(4): nn.JoinTable
}
(3): nn.View(512, 4, 4)
(4): nn.SpatialFullConvolution(512 -> 256, 4x4, 2,2, 1,1)
(5): nn.SpatialBatchNormalization (4D) (256)
(6): nn.ReLU
(7): nn.SpatialFullConvolution(256 -> 128, 4x4, 2,2, 1,1)
(8): nn.SpatialBatchNormalization (4D) (128)
(9): nn.ReLU
(10): nn.SpatialFullConvolution(128 -> 64, 4x4, 2,2, 1,1)
(11): nn.SpatialBatchNormalization (4D) (64)
(12): nn.ReLU
(13): nn.SpatialFullConvolution(64 -> 3, 4x4, 2,2, 1,1)
(14): nn.Tanh
}
Starting donkey with id: 1 seed: 334
table: 0x39d7abd8
/Users/anthonyyuan/torch/install/bin/luajit: ...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 1 callback] ...earning-master/pixelInterpolation/data/donkey_folder.lua:24: bad argument #2 to 'error' (number expected, got string)
stack traceback:
[C]: in function 'error'
...earning-master/pixelInterpolation/data/donkey_folder.lua:24: in main chunk
[C]: in function 'dofile'
...-demand-learning-master/pixelInterpolation/data/data.lua:38: in function <...-demand-learning-master/pixelInterpolation/data/data.lua:28>
[C]: in function 'xpcall'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:234: in function 'callback'
...nthonyyuan/torch/install/share/lua/5.1/threads/queue.lua:65: in function <...nthonyyuan/torch/install/share/lua/5.1/threads/queue.lua:41>
[C]: in function 'pcall'
...nthonyyuan/torch/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob'
[string " local Queue = require 'threads.queue'..."]:13: in main chunk
stack traceback:
[C]: in function 'error'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:264: in function 'synchronize'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:142: in function 'specific'
...honyyuan/torch/install/share/lua/5.1/threads/threads.lua:125: in function 'Threads'
...-demand-learning-master/pixelInterpolation/data/data.lua:26: in function 'new'
demo.lua:63: in main chunk
[C]: in function 'dofile'
...yuan/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x0107bbfbc0