Convnet Benchmarks. Test how fast different AI image recognition tools actually run.
github.com/soumith/convnet-benchmarks
Vaya's read on this project
Problem, audience, market, and the verdict — sign in to see it.
Updates
June 2017
- Merge pull request #129 from mitmul/chainer-v2
- Add Chainer V2
April 2017
- Merge pull request #127 from bryant1410/patch-1
- Fix README headers
March 2017
- Merge pull request #124 from hfp/master
- Updated deprecated initialization method, and avoid warning with rece…
January 2017
- Merge pull request #120 from annarev/update-tensorflow-functions
- Fixed a few more named arguments to softmax_cross_entropy_with_logits
- Update tensorflow functions to match the newest tensorflow version 1.…
October 2016
- Merge pull request #118 from bamos/master
- Update links to SpatialConvolutionMM.cu
- Merge pull request #117 from annarev/write-benchmark-output-to-csv
- Writing tensorflow benchmark timing information to CSV
- Merge pull request #115 from jonasrauber/patch-1
- fixed TensorFlow code that underestimated time
August 2016
- Merge pull request #113 from Shmuma/master
- Fix xrange usage, it's not python3-compatible
- Merge pull request #112 from SoraLab/fix-missing-brackets
- Merge pull request #111 from Hydrotoast/master
- Fix missing brackets in chainer's train_imagenet.py