Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Getting corrupted output image #12

Open
j-rev opened this issue Sep 12, 2017 · 0 comments
Open

Getting corrupted output image #12

j-rev opened this issue Sep 12, 2017 · 0 comments

Comments

@j-rev
Copy link

j-rev commented Sep 12, 2017

I am trying out local laplacian strong_1024 pre-trained model as
./hdrnet/bin/run.py ./pretrained_models/local_laplacian/strong_1024/ ./input.jpg ./
and getting corrupted output image (top several lines are totally corrupted and other parts of
the image has wrong color).

Could you help me what could be causing this issue ?

Below is snippet of log from running the above mentioned script.

2017-09-12 00:12:07.428452: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 0 with properties:
name: GeForce GTX 1080
major: 6 minor: 1 memoryClockRate (GHz) 1.7715
pciBusID 0000:01:00.0
Total memory: 7.92GiB
Free memory: 7.48GiB
2017-09-12 00:12:07.428462: I tensorflow/core/common_runtime/gpu/gpu_device.cc:976] DMA: 0
2017-09-12 00:12:07.428465: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 0: Y
2017-09-12 00:12:07.428469: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0)
[3193] INFO run.py:76 | Loading graph from ./pretrained_models/local_laplacian/strong_1024/upgraded_from_sig2017.ckpt-0.meta
WARNING:tensorflow:The saved meta_graph is possibly from an older release:
'model_variables' collection should be of type 'byte_list', but instead is of type 'node_list'.
[3193] WARNING tf_logging.py:90 | The saved meta_graph is possibly from an older release:
'model_variables' collection should be of type 'byte_list', but instead is of type 'node_list'.
2017-09-12 00:12:08.479604: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0)
[3193] INFO run.py:136 | Restoring weights from ./pretrained_models/local_laplacian/strong_1024/upgraded_from_sig2017.ckpt-0
[3193] INFO run.py:144 | Processing ./IMG_20170816_131836.jpg
[3193] INFO run.py:152 | Max level: 255
[3193] INFO run.py:153 | Max level: 255
[3193] INFO run.py:154 | Max level: 255
/opt/anaconda2/lib/python2.7/site-packages/skimage/transform/_warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.
warn("The default mode, 'constant', will be changed to 'reflect' in "

gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.4)
Python 2.7.13 :: Anaconda custom (64-bit)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant