Skip to content
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

Multi-pretrained weights: Add initial API and basic implementation #4671

Closed
datumbox opened this issue Oct 20, 2021 · 0 comments · Fixed by #4610, #4613, #4627, #4786 or #4792
Closed

Multi-pretrained weights: Add initial API and basic implementation #4671

datumbox opened this issue Oct 20, 2021 · 0 comments · Fixed by #4610, #4613, #4627, #4786 or #4792
Labels
module: models.quantization Issues related to the quantizable/quantized models module: models prototype

Comments

@datumbox
Copy link
Contributor

datumbox commented Oct 20, 2021 •
edited
Loading

🚀 The feature

Part of #4611

Add the initial API mechanism for the Multi-pretrained weights:

  • The WeightEntry and Weights classes.
  • The necessary preset transforms.
  • The meta information needed for the models.

Moreover provide basic implementations for the following models:

  • ResNet50
  • FasterRCNN + ResNet50
  • Quantized ResNet50
@datumbox datumbox added prototype module: models module: models.quantization Issues related to the quantizable/quantized models labels Oct 20, 2021
This was referenced Oct 20, 2021
Merged
Merged
Merged
This was linked to pull requests Oct 29, 2021
Adding multiweight support for regnet prototype models #4786
Merged
Adding multiweight support for shufflenetv2 prototype model #4792
Merged
Adding multiweight support for googlenet prototype model #4813
Merged
Adding multiweight support for squeezenet prototype model #4817
Merged
Adding multiweight support for inception prototype model #4821
Merged
@datumbox datumbox mentioned this issue Nov 2, 2021
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
module: models.quantization Issues related to the quantizable/quantized models module: models prototype
Projects
None yet
Milestone
No milestone
1 participant
@datumbox