Closed tss12 closed 6 years ago
looks like a memory issue.
@anishathalye thanks, maybe I should try tensorflow with gpu.
This is not an error, just warnings. TF can run faster if you compile it from source. See details in this question.
I think he's talking about the "killed" at the end, which is probably from the oom killer. I don't think the question is about the warnings.
I see, thanks buddy
I have the same issue @tss12
I get this error when using style images that are too large, try smaller or resizing.
@maitreepasad hello,it may be your mashine memory is too small.
@kthordarson and how much time does the code take to run?
Yes I think
I ran it on Floyd hub.. ran successfully! Thanks
On Wed, 18 Apr 2018 11:25 tss12, notifications@github.com wrote:
@maitreepasad https://github.com/maitreepasad hello,it may be your mashine memory is too small.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/anishathalye/neural-style/issues/112#issuecomment-382270737, or mute the thread https://github.com/notifications/unsubscribe-auth/Ab6oIpPKC29yt9Mt5mrnn4UcuVm5JLmZks5tptU5gaJpZM4R5OQK .
@maitreepasad congratulation,only with cpu?
No with GPU Image size approx 500*400 1000 iterations - 7 minutes
On Wed, 18 Apr 2018 11:36 tss12, notifications@github.com wrote:
@maitreepasad https://github.com/maitreepasad congratulation,only with cpu?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/anishathalye/neural-style/issues/112#issuecomment-382272855, or mute the thread https://github.com/notifications/unsubscribe-auth/Ab6oInuHZCunZXyC5D0wyIIIXqSPZ6E1ks5tptfLgaJpZM4R5OQK .
2018-02-05 17:40:45.026070: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations. 2018-02-05 17:40:45.026107: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations. 2018-02-05 17:40:45.026115: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. 2018-02-05 17:40:45.026123: W 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. 2018-02-05 17:40:45.026130: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX512F instructions, but these are available on your machine and could speed up CPU computations. 2018-02-05 17:40:45.026137: W 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. killed
———————— when I run the code python neural_style.py --content 'examples/1-content.jpg' --styles 'examples/1-style.jpg' --output 'examples/my1.jpg' ,then give me some warring and killed,it is may be tensorflow`s trouble,but I do not should I do.