karpathy / neuraltalk2

Efficient Image Captioning code in Torch, runs on GPU
5.49k stars 1.26k forks source link

eval.lua with cpu, read error #165

Open sevgiturgut opened 7 years ago

sevgiturgut commented 7 years ago

When i run eval.lua, i got this:

#th eval.lua -model /home/sevgi/Downloads/neuraltalk2-master/model_id1-501-1448236541.t7_cpu.t7 -image_folder /home/sevgi/Downloads/neuraltalk2-master/img/ -num_images -1 -batch_size 1 -gpuid -1
/home/sevgi/torch/install/bin/luajit: /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:351: read error: read 24000749 blocks instead of 137407040 at /tmp/luarocks_torch-scm-1-1960/torch7/lib/TH/THDiskFile.c:353
stack traceback:
    [C]: in function 'read'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:351: in function </home/sevgi/torch/install/share/lua/5.1/torch/File.lua:245>
    [C]: in function 'read'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/nn/Module.lua:192: in function 'read'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/nn/Module.lua:192: in function 'read'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
    /home/sevgi/torch/install/share/lua/5.1/torch/File.lua:409: in function 'load'
    eval.lua:69: in main chunk
    [C]: in function 'dofile'
    ...evgi/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
    [C]: at 0x00405d50
lymrty commented 6 years ago

@sevgiturgut , so how do you solve this problem, would you like to share your solution? thanks