search

jiangsutx / SRN-Deblur

Repository for Scale-recurrent Network for Deep Image Deblurring
http://www.xtao.website/projects/srndeblur/srndeblur_cvpr18.pdf
MIT License
714 stars 184 forks source link

save_path is not a valid checkpoint #64

Closed lin-peiyi closed 3 years ago

lin-peiyi commented 3 years ago

Thanks for your sharing. How can I deal with this problem? ValueError: The passed save_path is not a valid checkpoint: ./checkpoints\color\deblur.model-523000

jiangsutx commented 3 years ago

Please check whether the file exists? If not, you need to first download the model file, using ./checkpoints/download_model.sh

lin-peiyi commented 3 years ago

Please check whether the file exists? If not, you need to first download the model file, using ./checkpoints/download_model.sh

Yes,I haved downloaded it.Whether this model has to be run in linxus?Because I use win10,appearing a lot of bugs.

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for ./checkpoints\color\deblur.model-523000 [[Node: save/RestoreV2_83 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_83/tensor_names, save/RestoreV2_83/shape_and_slices)]]

sherlybe commented 3 years ago

so, do u run it sucessfully?

jiangsutx commented 3 years ago

Please check whether the file exists? If not, you need to first download the model file, using ./checkpoints/download_model.sh

Yes,I haved downloaded it.Whether this model has to be run in linxus?Because I use win10,appearing a lot of bugs.

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for ./checkpoints\color\deblur.model-523000 [[Node: save/RestoreV2_83 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_83/tensor_names, save/RestoreV2_83/shape_and_slices)]]

Maybe it is because the path ./checkpoints\color\deblur.model-523000 uses a mix of / and \ ?

lin-peiyi commented 3 years ago

so, do u run it sucessfully?

lin-peiyi commented 3 years ago

so, do u run it sucessfully?

I can't open the ./checkpoints/download_model.sh in win10,so I have used ubuntu to run it,that's ok. So maybe you can have a try. @sherlybe

lin-peiyi commented 3 years ago

Please check whether the file exists? If not, you need to first download the model file, using ./checkpoints/download_model.sh

Yes,I haved downloaded it.Whether this model has to be run in linxus?Because I use win10,appearing a lot of bugs. NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for ./checkpoints\color\deblur.model-523000 [[Node: save/RestoreV2_83 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_83/tensor_names, save/RestoreV2_83/shape_and_slices)]]

Maybe it is because the path ./checkpoints\color\deblur.model-523000 uses a mix of / and \ ?

Thank you very much.I can run it in ubuntu.