Could you mind sharing pre-trained models for 64*64 experiments?

[happsky]

Could you mind sharing pre-trained models for 64*64 experiments?

[kregmi]

Please find them here.

[happsky]

Hi, Kergmi
When I test the 64X64 model with command DATA_ROOT=/home/datasets/dayton_g2a_64 name=dayton_64_64_g2a_fork which_direction=g2a batchSize=16 phase=test which_epoch=100 loadSize=64 fineSiz=64 th test_fork.lua, I got the following error,

processing batch 1
/home/csdept/torch/install/bin/luajit: ...e/csdept/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 1 callback] /home/csdept/torch/install/share/lua/5.1/image/init.lua:569: image.crop: crop goes outside bounds of src
stack traceback:
[C]: in function 'cropNoScale'
/home/csdept/torch/install/share/lua/5.1/image/init.lua:569: in function 'crop'
...ects/cross_view_image_synthesis_2/data/donkey_folder.lua:82: in function 'preprocessAandB'
...ects/cross_view_image_synthesis_2/data/donkey_folder.lua:124: in function 'sampleHookTrain'
...t/projects/cross_view_image_synthesis_2/data/dataset.lua:339: in function 'getByClass'
...t/projects/cross_view_image_synthesis_2/data/dataset.lua:372: in function <...t/projects/cross_view_image_synthesis_2/data/dataset.lua:364>
[C]: in function 'xpcall'
...e/csdept/torch/install/share/lua/5.1/threads/threads.lua:234: in function 'callback'
/home/csdept/torch/install/share/lua/5.1/threads/queue.lua:65: in function </home/csdept/torch/install/share/lua/5.1/threads/queue.lua:41>
[C]: in function 'pcall'
/home/csdept/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'
...e/csdept/torch/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob'
...dept/projects/cross_view_image_synthesis_2/data/data.lua:85: in function 'getBatch'
test_fork.lua:114: in main chunk
[C]: in function 'dofile'
...dept/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50

Do you have any idea or need I change some hyper-parameters? Thank you very much.

[kregmi]

DATA_ROOT=/home/datasets/dayton_g2a_64 name=dayton_64_64_g2a_fork which_direction=g2a batchSize=16 phase=test which_epoch=100 loadSize=64 fineSiz=64 th test_fork.lua
Is this typo the cause for error? Let me know.

[happsky]

It was, thanks a lot.