Skip to content

Add CSPResNet #117

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 8 commits into from
May 18, 2020
Merged

Add CSPResNet #117

merged 8 commits into from
May 18, 2020

Conversation

littletomatodonkey
Copy link
Collaborator

@littletomatodonkey littletomatodonkey commented May 14, 2020 •
edited
Loading

Based on the same training strategy with ResNet50(Top1 Acc 76.5%, models size 99M), CSPResNet50 Top1 Acc is 77.17% on ImageNet 1k val(while the model size is just 86M).

  • Note: resize short size and crop size are 256 for CSPResNet50 eval process.

Inference benchmark on T4 GPU

Models Crop Size Resize Short Size FP16
Batch Size=1
(ms)		 FP16
Batch Size=4
(ms)		 FP16
Batch Size=8
(ms)		 FP32
Batch Size=1
(ms)		 FP32
Batch Size=4
(ms)		 FP32
Batch Size=8
(ms)
CSPResNet50 256 256 3.08307 5.96324 9.86307 3.79766 9.24683 16.68879

@littletomatodonkey littletomatodonkey merged commit 81c9a6d into PaddlePaddle:master May 18, 2020
@littletomatodonkey littletomatodonkey deleted the cspnet branch February 19, 2021 05:04
HydrogenSulfate pushed a commit to HydrogenSulfate/PaddleClas that referenced this pull request Oct 18, 2023
@xingfeng01
update equation definition (PaddlePaddle#117)
2ca2af1 
* update pde definition

* update weight definition

* fix api ci

* fix n-s defination

* fix weight in ns def

* fix n-s init error

* fix dt undef error
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@littletomatodonkey