You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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 "
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)
The text was updated successfully, but these errors were encountered: