Skip to content

Neuron trained with Human face data fails to execute in this code #39

@harshithabk

Description

@harshithabk

Hi,
By referring the below link:
#24
I trained train.lua with human face data in context encoder https://github.com/pathak22/context-encoder

The trained model, when tested, executes in context encoder.
However the same trained model fails to execute in Faster-High-Res-Neural-Inpainting source code.
When i run the command: th run_content_network.lua,
I get the below error log:

Found Environment variable CUDNN_PATH = /home/test/cudnn-8.0-linux-x64-v5.0-ga/cuda/lib64/libcudnn.so.5.0.5{
gpu : 1
model_file : "models/inpaintCenterHumanFaceNoRetrain_500_net_G.t7"
overlapPred : 4
fineSize : 128
}
/home/test/torch/install/bin/luajit: /home/test/torch/install/share/lua/5.1/nn/Container.lua:67:
In 1 module of nn.Sequential:
In 1 module of nn.Sequential:
/home/test/torch/install/share/lua/5.1/nn/THNN.lua:110: bad argument #3 to 'v' (cannot convert 'struct THDoubleTensor *' to 'struct THFloatTensor *')
stack traceback:
[C]: in function 'v'
/home/test/torch/install/share/lua/5.1/nn/THNN.lua:110: in function 'SpatialConvolutionMM_updateOutput'
...ya/torch/install/share/lua/5.1/nn/SpatialConvolution.lua:79: in function <...ya/torch/install/share/lua/5.1/nn/SpatialConvolution.lua:76>
[C]: in function 'xpcall'
/home/test/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
/home/test/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function </home/test/torch/install/share/lua/5.1/nn/Sequential.lua:41>
[C]: in function 'xpcall'
/home/test/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
/home/test/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
run_content_network.lua:41: in main chunk
[C]: in function 'dofile'
...est/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50

WARNING: If you see a stack trace below, it doesn't point to the place where this error occurred. Please use only the one above.
stack traceback:
[C]: in function 'error'
/home/test/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors'
/home/test/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
run_content_network.lua:41: in main chunk
[C]: in function 'dofile'
...est/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50

I referred the link torch/nn#981
to resolve this issue.
However its not resolved yet.
I was wondering when the model is executing in context encoder, what could be the reason for this error in Faster-High-Res-Neural-Inpainting
Could you help me regarding the same?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions