-
Notifications
You must be signed in to change notification settings - Fork 21
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add image classification benchmark to vSwarm #605
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks, Manyi.
- Please add copyrights to all the files (our copyrights or the original copyrights if borrowed)
- are Val-map and get-pip.py files are necessary?
- Add CI
|
||
The benchmark implements `Resnet50 model inference` on `Imagenet2012 val` dataset to do image classification. The implementation references [MLPerf Edge Inference Suite](https://github.com/mlcommons/inference/tree/master/vision/classification_and_detection). | ||
|
||
The benchmark is implementated in Python. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Redundant
@@ -0,0 +1,69 @@ | |||
FROM ubuntu:16.04 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Super old, must be 20
COPY benchmarks/image_classification/python /app | ||
|
||
# Prepare dataset and model | ||
# Here's the full dataset |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we need the full dataset?
import imagenet | ||
|
||
from proto.image_classification import image_classification_pb2 | ||
# import image_classification_pb2 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Clean
@@ -0,0 +1,50 @@ | |||
# MIT License | |||
|
|||
# Copyright (c) 2023 Hyscale lab |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
HyScale lab and vSwarm team
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- remove binaries from the commit history
ILSVRC2012_img_val.zip
andresnet50_v1.pb.zip
. if necessary, it should be added to Git LFS (you can find examples in vHive repobin/
folder) - merge the PR in the proto repo first
Add image classification benchmark to vSwarm