Searching for Better ViT Baselines
Collection
Exploring ViT hparams and model shapes for the GPU poor (between tiny and base).
•
25 items
•
Updated
•
16
Naga Durga Harish Kanamarlapudi
nagaharish
AI & ML interests
Interested in robotics and AI for health care.
Recent Activity
upvoted
a
collection
29 days ago
Searching for Better ViT Baselines
updated
a collection
6 months ago
Battle of backbones
updated
a collection
6 months ago
Battle of backbones
Organizations
None yet
nagaharish's activity
upvoted
a
collection
29 days ago
updated
a
collection
6 months ago
liked
a
Space
6 months ago
reacted to
rwightman's
post with 🚀🔥
6 months ago
Post
2064
The latest timm validation & test set results are now viewable by a leaderboard space:
timm/leaderboard
As of yesterday, I updated all of the results for ImageNet , ImageNet-ReaL, ImageNet-V2, ImageNet-R, ImageNet-A, and Sketch sets. The csv files can be found in the GH repo https://github.com/huggingface/pytorch-image-models/tree/main/results
Unfortunately the latest benchmark csv files are not yet up to date, there are some gaps in dataset results vs throughput/flop numbers impact the plots.
h/t to @MohamedRashad for making the first timm leaderboard.
As of yesterday, I updated all of the results for ImageNet , ImageNet-ReaL, ImageNet-V2, ImageNet-R, ImageNet-A, and Sketch sets. The csv files can be found in the GH repo https://github.com/huggingface/pytorch-image-models/tree/main/results
Unfortunately the latest benchmark csv files are not yet up to date, there are some gaps in dataset results vs throughput/flop numbers impact the plots.
h/t to @MohamedRashad for making the first timm leaderboard.
- 1 reply
upvoted
a
paper
12 months ago
updated
a
model
about 2 years ago