MobileOne#
The ResNet model is based on the “An Improved One millisecond Mobile Backbone” paper.
Architecture overview#
This architecture optimizes the model for inference speed at inference time on mobile device.
The key takeaways from the paper are the following:
reuse the reparametrization concept of RepVGG while adding overparametrization in the block branches.
each block is composed of two consecutive reparametrizeable blocks (in a similar fashion than RepVGG): a depth-wise convolutional block, a point-wise convolutional block.
Model builders#
The following model builders can be used to instantiate a MobileOne model, with or
without pre-trained weights. All the model builders internally rely on the
holocron.models.classification.mobileone.MobileOne
base class. Please refer to the source
code for
more details about this class.
|
MobileOne-S0 from "An Improved One millisecond Mobile Backbone" |
|
MobileOne-S1 from "An Improved One millisecond Mobile Backbone" |
|
MobileOne-S2 from "An Improved One millisecond Mobile Backbone" |
|
MobileOne-S3 from "An Improved One millisecond Mobile Backbone" |