CycleGAN
CycleGAN copied to clipboard
junyanz
I can't get the result file
I've done the tutorial to generate Paul Cézanne style images: But i can't get the result in ./results/style_cezanne_pretrained/latest_test/index.html.And There is no results folder exists.I don't know the reason.Thank you!Wait for your reply! /home/lab_1009/torch/install/bin/luajit: ./options.lua:135: attempt to index global 'fd' (a nil value) stack traceback: ./options.lua:135: in function 'parse_options' test.lua:12: in main chunk [C]: in function 'dofile' ...1009/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: at 0x00405d50
I guess you failed to create the output directory. See more details here. Make sure you can create this text file under the directory.
fd = io.open(paths.concat(opt.checkpoints_dir, opt.name, 'opt_' .. mode .. '.txt'), 'w')
I also meet the same problem, what's worse——I can't even finish the step Apply a Pre-trained Model
.It''s like:
I don't know the reason.Is there any way to solve it? @junyanz Thanks!!!
I also meet the same problem, what's worse——I can't even finish the step Apply a Pre-trained Model .It''s like:
I also meet the same problem, what's worse——I can't even finish the step Apply a Pre-trained Model .It''s like:
Hello, I meet the same problem. When I input that DATA_ROOT=./datasets/ae_photos name=style_cezanne_pretrained model=one_direction_test phase=test loadSize=256 fineSize=256 resize_or_crop="scale_width" th test.lua, the error is appeared. I checked there is no style_cezanne_pretrained_model in pre-trained file. How did you solve this problem?
@xixilzh It seems that the program fails to create the directory and texture file. Please double check if you have the permission.
fd = io.open(paths.concat(opt.checkpoints_dir, opt.name, 'opt_' .. mode .. '.txt'), 'w')