tensorflow-yolo-v3$ python demo.py --input_img data/dog.jpg --output_img data/out_dog.jpg --frozen_model frozen_darknet_yolov3_model.pb
/home/wootion/anaconda3/lib/python3.6/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
Loaded graph in 0.87s
2019-08-20 14:21:41.015756: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-08-20 14:21:41.173395: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1405] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.683
pciBusID: 0000:02:00.0
totalMemory: 10.92GiB freeMemory: 10.00GiB
2019-08-20 14:21:41.286852: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1405] Found device 1 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.683
pciBusID: 0000:03:00.0
totalMemory: 10.92GiB freeMemory: 10.75GiB
2019-08-20 14:21:41.287620: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1484] Adding visible gpu devices: 0, 1
2019-08-20 14:21:41.627585: I tensorflow/core/common_runtime/gpu/gpu_device.cc:965] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-08-20 14:21:41.627621: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0 1
2019-08-20 14:21:41.627631: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] 0: N Y
2019-08-20 14:21:41.627637: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] 1: Y N
2019-08-20 14:21:41.627999: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1097] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 8941 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:02:00.0, compute capability: 6.1)
2019-08-20 14:21:41.713771: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1097] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 8942 MB memory) -> physical GPU (device: 1, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0, compute capability: 6.1)
Predictions found in 3.70s
I have 2 gtx1080Ti on my computer,
All the parameters are default except 'gpu_memory_fraction' as it has to be < 1,I set it to 0.8.
The prediction cost 3.7s ,the same as running on CPU.
Please tell me what's the wrong?
I have 2 gtx1080Ti on my computer, All the parameters are default except 'gpu_memory_fraction' as it has to be < 1,I set it to 0.8. The prediction cost 3.7s ,the same as running on CPU. Please tell me what's the wrong?