Thanks for sharing this fantastic work.
I'm wondering if it's typical for a 1280x720 image to take 30 seconds to process. Could it be that my GPU is not being utilized properly?
When I run the same images with ESTRNN it only takes 1 or 2 seconds per frame.
"2022-01-15 23:44:20.211283: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2022-01-15 23:44:20.211577: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
[] Reading checkpoints...
[] Reading intermediate checkpoints... Success
Saving results: ./testing_res\00000000.png ... 29.047s
Saving results: ./testing_res\00000001.png ... 28.678s"
Thanks for sharing this fantastic work. I'm wondering if it's typical for a 1280x720 image to take 30 seconds to process. Could it be that my GPU is not being utilized properly? When I run the same images with ESTRNN it only takes 1 or 2 seconds per frame.
"2022-01-15 23:44:20.211283: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations. 2022-01-15 23:44:20.211577: W c:\tf_jenkins\home\workspace\release-win\m\windows\py\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations. [] Reading checkpoints... [] Reading intermediate checkpoints... Success Saving results: ./testing_res\00000000.png ... 29.047s Saving results: ./testing_res\00000001.png ... 28.678s"