llSourcell / YOLO_Object_Detection

This is the code for "YOLO Object Detection" by Siraj Raval on Youtube
GNU General Public License v3.0
1.73k stars 795 forks source link

How to use GPU on iMac with ATI Radeon #2

Open arsen3d opened 6 years ago

arsen3d commented 6 years ago

Running entirely on CPU 2017-11-16 23:00:58.418427: 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 Finished in 9.086707830429077s

GVA info: Successfully connected to the Intel plugin, offline Gen75 Press [ESC] to quit demo 0.884 FPS

arsen3d commented 6 years ago

imac5k2015:darkflow arsen$ flow --model cfg/yolo.cfg --load yolo.weights --demo video.mp4 --gpu 1.0 --saveVideo /Users/arsen/anaconda3/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6 return f(*args, **kwds)

Parsing ./cfg/yolo.cfg Parsing cfg/yolo.cfg Loading yolo.weights ... Successfully identified 203934260 bytes Finished in 1.447549819946289s Model has a coco model name, loading coco labels.

Building net ... Source | Train? | Layer description | Output size -------+--------+----------------------------------+--------------- | | input | (?, 608, 608, 3) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 608, 608, 32) Load | Yep! | maxp 2x2p0_2 | (?, 304, 304, 32) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 304, 304, 64) Load | Yep! | maxp 2x2p0_2 | (?, 152, 152, 64) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 152, 152, 128) Load | Yep! | conv 1x1p0_1 +bnorm leaky | (?, 152, 152, 64) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 152, 152, 128) Load | Yep! | maxp 2x2p0_2 | (?, 76, 76, 128) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 76, 76, 256) Load | Yep! | conv 1x1p0_1 +bnorm leaky | (?, 76, 76, 128) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 76, 76, 256) Load | Yep! | maxp 2x2p0_2 | (?, 38, 38, 256) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 38, 38, 512) Load | Yep! | conv 1x1p0_1 +bnorm leaky | (?, 38, 38, 256) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 38, 38, 512) Load | Yep! | conv 1x1p0_1 +bnorm leaky | (?, 38, 38, 256) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 38, 38, 512) Load | Yep! | maxp 2x2p0_2 | (?, 19, 19, 512) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 19, 19, 1024) Load | Yep! | conv 1x1p0_1 +bnorm leaky | (?, 19, 19, 512) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 19, 19, 1024) Load | Yep! | conv 1x1p0_1 +bnorm leaky | (?, 19, 19, 512) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 19, 19, 1024) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 19, 19, 1024) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 19, 19, 1024) Load | Yep! | concat [16] | (?, 38, 38, 512) Load | Yep! | conv 1x1p0_1 +bnorm leaky | (?, 38, 38, 64) Load | Yep! | local flatten 2x2 | (?, 19, 19, 256) Load | Yep! | concat [27, 24] | (?, 19, 19, 1280) Load | Yep! | conv 3x3p1_1 +bnorm leaky | (?, 19, 19, 1024) Load | Yep! | conv 1x1p0_1 linear | (?, 19, 19, 425) -------+--------+----------------------------------+--------------- GPU mode with 1.0 usage 2017-11-17 09:25:00.273421: 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 Finished in 8.623509168624878s

GVA info: Successfully connected to the Intel plugin, offline Gen75 Press [ESC] to quit demo 1.128 FPS

PandaWhoCodes commented 6 years ago

You need to compile your tensorflow version to use OpenCL

arsen3d commented 6 years ago

Any idea if there are docs to do this?

mindfulme commented 6 years ago

Here https://www.tensorflow.org/install/install_sources