Skip to content

Instantly share code, notes, and snippets.

@tomrunia

tomrunia/README.md

Created March 3, 2016 15:23
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save tomrunia/941bc1a6ca7a5bb2e991 to your computer and use it in GitHub Desktop.
Save tomrunia/941bc1a6ca7a5bb2e991 to your computer and use it in GitHub Desktop.
Download ZIP
Caffe model benchmarks: average classification time per image on MS-COCO (GPU Titan X)
Raw
README.md

Caffe Classification

Classification Speed Benchmark

Table lists average classification times per image (milliseconds). Averages are computed over classification of 100 images from MS-COCO validation set. For the VGG networks a very high variance in classification times was observed, some images were classified fast while most of them took more processing time that other network configurations.

Model Input Size CPU (ms) GPU (ms)
bvlc_alexnet.caffemodel 227x227 314.7 20.1
bvlc_googlenet.caffemodel 224x224 490.7 33.6
VGG_ILSVRC_16_layers.caffemodel 224x224 758.2 35.7
VGG_ILSVRC_19_layers.caffemodel 224x224 >1000 34.3
ResNet-50-model.caffemodel 224x224 >1000 50.4
ResNet-101-model.caffemodel 224x224 >1000 84.6
ResNet-152-model.caffemodel 224x224 >1000 116.1
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment