Oleg Zabluda's blog
Tuesday, March 14, 2017
 
Github/jcjohnson/cnn-benchmarks
Github/jcjohnson/cnn-benchmarks
"""

Benchmarks for popular convolutional neural network models on CPU and different GPUs, with and without cuDNN.

Some general conclusions from this benchmarking:

Pascal Titan X > GTX 1080

ResNet > VGG: ResNet-50 is faster than VGG-16 and more accurate than VGG-19 (7.02 vs 9.0); ResNet-101 is about the same speed as VGG-19 but much more accurate than VGG-16 (6.21 vs 9.0).

We benchmark all models with a minibatch size of 16 and an image size of 224 x 224; this allows direct comparisons between models, and allows all but the ResNet-200 model to run on the GTX 1080, which has only 8GB of memory.

The following models are benchmarked:

Network Layers Top-1 error Top-5 error Speed (ms) Citation
AlexNet 8 42.90 19.80 14.56 [1]
Inception-V1 22 - 10.07 39.14 [2]
VGG-16 16 27.00 8.80 128.62 [3]
VGG-19 19 27.30 9.00 147.32 [3]
ResNet-18 18 30.43 10.76 31.54 [4]
ResNet-34 34 26.73 8.74 51.59 [4]
ResNet-50 50 24.01 7.02 103.58 [4]
ResNet-101 101 22.44 6.21 156.44 [4]
ResNet-152 152 22.16 6.16 217.91 [4]
ResNet-200
"""
https://github.com/jcjohnson/cnn-benchmarks
https://github.com/jcjohnson/cnn-benchmarks

Labels:


- posted by Oleg Zabluda @ 9:43 PM | permalink | | | technorati | bloglines | feedster
| |

Home

Powered by Blogger