Add SSD to benchmark model repo
Open
Nobody has claimed this yet.
hackathon_candidate
- Dominant language
- Python
- Stars
- 1k
- Forks
- 346
- PR merge metrics
- No merged PRs in 30d
Description
This is in pytorch/hub: https://pytorch.org/hub/nvidia_deeplearningexamples_ssd/.
There's some evidence that this can be made much faster (up to 3x) with some graph optimizations: https://paulbridger.com/posts/video-analytics-deepstream-pipeline/
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the SSD model in the linked PyTorch Hub entry and the benchmark repository's existing model integrations. Compare the model's expected inputs and execution path with current benchmarks, then verify that SSD is included with a reproducible performance measurement and any documented graph-optimization result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100