jcjohnson / jcjohnson/cnn-benchmarks

openCL branch of caffe reports much higher speeds

Open
#12 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
2.5k
Forks
402
PR merge metrics
No merged PRs in 30d

Description

on [OpenCL-caffe](https://github.com/amd/OpenCL-caffe), there are performance matrices claiming speeds of about 4ms per image for training AlexNet with Radeon R290X, Considering this GPU is much weaker than a GTX 1080, these figures seem very weird compared with the 20ms in your tests.

What's your take on this?

Contributor guide

No contributing guide indexed for this repository

Research direction

Compare the OpenCL-caffe performance matrices for AlexNet training on the Radeon R290X with the benchmark results reporting about 20ms per image. Start by reviewing the benchmark methodology and hardware assumptions described in the issue and linked project. Done means explaining the discrepancy or identifying a reproducible benchmarking error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.