warmspringwinds / pytorch-segmentation-detection

Image Segmentation and Object Detection in Pytorch
MIT License
746 stars 170 forks source link

No such file or directory: 'resnet_34_8s_66.pth' #5

Closed akashgoyal closed 6 years ago

akashgoyal commented 6 years ago

Hi @warmspringwinds I am getting - IOError: [Errno 2] No such file or directory: 'resnet_34_8s_66.pth' when running resnet_34_8s_demo.ipynb

Not able to figure out when and how the model will generate. Any clue on the next step .

Thanks Akash

warmspringwinds commented 6 years ago

Hi @akashgoyal , Download the respective file from a dropbox link here https://github.com/warmspringwinds/pytorch-segmentation-detection#deeplab-semantic-image-segmentation-with-deep-convolutional-nets-atrous-convolution-and-fully-connected-crfs

Let me know if you have any further complications.

akashgoyal commented 6 years ago

Great !! Thank you so much :)

akashgoyal commented 6 years ago

@warmspringwinds I am still getting that error. I am not able to figure out from where the code is trying to read model. Can you please also specify where the model has to be placed ?

Thanks

warmspringwinds commented 6 years ago

Hi,

place it at the same directory where you are running the ipython notebook or specify the full absolute path to your model file -- also make sure that you specified the name of the file correctly.

2018-01-11 12:11 GMT-05:00 Akash notifications@github.com:

@warmspringwinds https://github.com/warmspringwinds I am still getting that error. Can you please also tell where the model has to be placed ?

Thanks

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/warmspringwinds/pytorch-segmentation-detection/issues/5#issuecomment-356995917, or mute the thread https://github.com/notifications/unsubscribe-auth/ACYrByaQh9G8_yZvH04XAlJWwwWEfeUBks5tJkDQgaJpZM4Raulm .

akashgoyal commented 6 years ago

Specifying absolute path worked for me. Thanks a ton.

warmspringwinds commented 6 years ago

You are welcome :)