Created
January 16, 2018 04:03
-
-
Save kmamykin/79428e31020b158d7aa18656e4f4c539 to your computer and use it in GitHub Desktop.
plaidbench for Macbook Pro
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
``` | |
$ python plaidbench.py --no-plaid mobilenet | |
Current network being run : mobilenet | |
Running 1024 examples with mobilenet, batch size 1 | |
~/Projects/plaidml-test/.direnv/python-3.5.2/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. | |
from ._conv import register_converters as _register_converters | |
Using TensorFlow backend. | |
2018-01-15 22:49:34.785024: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA | |
Model loaded. | |
Compiling and running initial batch, batch_size=1 | |
Example finished, elapsed: 0.2697739601135254 (compile), 82.26961827278137 (execution) | |
``` | |
``` | |
$ python plaidbench.py --plaid mobilenet | |
Using PlaidML backend. | |
~/Projects/plaidml-test/.direnv/python-3.5.2/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. | |
from ._conv import register_converters as _register_converters | |
1 #!/usr/bin/env python | |
Current network being run : mobilenet | |
Running 1024 examples with mobilenet, batch size 1 | |
INFO:plaidml:b'Opening device "iris_pro.0"' | |
Model loaded. | |
Compiling and running initial batch, batch_size=1 | |
Example finished, elapsed: 3.5091819763183594 (compile), 19.298163890838623 (execution) | |
``` | |
``` | |
$ python plaidbench.py --no-plaid mobilenet | |
Current network being run : mobilenet | |
Running 1024 examples with mobilenet, batch size 1 | |
~/Projects/plaidml-test/.direnv/python-3.5.2/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. | |
from ._conv import register_converters as _register_converters | |
Using TensorFlow backend. | |
2018-01-15 22:52:00.121515: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA | |
Model loaded. | |
Compiling and running initial batch, batch_size=1 | |
Example finished, elapsed: 0.2799251079559326 (compile), 79.63189053535461 (execution) | |
``` | |
``` | |
$ python plaidbench.py --plaid mobilenet | |
Using PlaidML backend. | |
~/Projects/plaidml-test/.direnv/python-3.5.2/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. | |
from ._conv import register_converters as _register_converters | |
Current network being run : mobilenet | |
Running 1024 examples with mobilenet, batch size 1 | |
INFO:plaidml:b'Opening device "iris_pro.0"' | |
Model loaded. | |
Compiling and running initial batch, batch_size=1 | |
Example finished, elapsed: 3.506929874420166 (compile), 19.07184410095215 (execution) | |
``` | |
``` | |
$ python vgg.py | |
~/Projects/plaidml-test/.direnv/python-3.5.2/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. | |
from ._conv import register_converters as _register_converters | |
INFO:plaidml:b'Opening device "iris_pro.0"' | |
Running initial batch (compiling tile program) | |
INFO:plaidml:b'Analyzing Ops: 66 of 195 operations complete' | |
INFO:plaidml:b'Analyzing Ops: 122 of 195 operations complete' | |
Timing inference... | |
Ran in 12.404700994491577 seconds | |
``` |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment