search

jcjohnson / neural-style

Torch implementation of neural style algorithm
MIT License
18.31k stars 2.7k forks source link

New to Coding - Issues Running Neural Style #467

Open epoworker opened 5 years ago

epoworker commented 5 years ago

As the title suggests, I am using Neural style with no previous Python or general coding experience. I have been following https://www.youtube.com/watch?v=3AnXiDksblA tutorial to try and process video through Neural Style, but keep coming across errors.

The code I have entered is as follows: for a in 'seq -w 000 100'; do th neural_style.lua \ -style_image /home/ethanw/Downloads/ATTAMPTFOURR/PROCESS/Style/16684lpr_257494bc2fb728b.jpg \ -content_image /home/ethanw/Downloads/ATTAMPTFOURR/PROCESS/Light1/Light$a.tif \ -output_image /home/ethanw/Downloads/ATTAMPTFOURR/PROCESS/Output/Light1/Light_result_$a.jpg \ -gpu 0 \ -image_size 626 \ -style_weight 'shuf -i1100-1200 -n1' \ -backend nn \ -seed 100 \ -num_iterations 400 \ -content_weight 'shuf -i500-530 -n1' \ -init random \ -normalize_gradients ; done From this code, I get back: invalid argument: -w Usage: [options] -style_image Style target image [examples/inputs/seated-nude.jpg] -style_blend_weights [nil] -content_image Content target image [examples/inputs/tubingen.jpg] -image_size Maximum height / width of generated image [512] -gpu Zero-indexed ID of the GPU to use; for CPU mode set -gpu = -1 [0] -multigpu_strategy Index of layers to split the network across GPUs [] -content_weight [5] -style_weight [100] -tv_weight [0.001] -num_iterations [1000] -normalize_gradients [false] -init random|image [random] -init_image [] -optimizer lbfgs|adam [lbfgs] -learning_rate [10] -lbfgs_num_correction [0] -print_iter [50] -save_iter [100] -output_image [out.png] -style_scale [1] -original_colors [0] -pooling max|avg [max] -proto_file [models/VGG_ILSVRC_19_layers_deploy.prototxt] -model_file [models/VGG_ILSVRC_19_layers.caffemodel] -backend nn|cudnn|clnn [nn] -cudnn_autotune [false] -seed [-1] -content_layers layers for content [relu4_2] -style_layers layers for style [relu1_1,relu2_1,relu3_1,relu4_1,relu5_1] -output_image: command not found

As far as I know, I have all the dependencies installed, and have tried running the code in both the default and neural-style directories.

Any help or clarification as to what I might be getting wrong would be much appreciated, thanks for bearing with me.

AndreV84 commented 5 years ago

try with a simple piece of code starting with th neural_style.lua