> [An Improved One millisecond Mobile Backbone](https://arxiv.org/abs/2206.04040)
<!-- [ALGORITHM] -->
## Abstract
Efficient neural network backbones for mobile devices are often optimized for metrics such as FLOPs or parameter count. However, these metrics may not correlate well with latency of the network when deployed on a mobile device. Therefore, we perform extensive analysis of different metrics by deploying several mobile-friendly networks on a mobile device. We identify and analyze architectural and optimization bottlenecks in recent efficient neural networks and provide ways to mitigate these bottlenecks. To this end, we design an efficient backbone MobileOne, with variants achieving an inference time under 1 ms on an iPhone12 with 75.9% top-1 accuracy on ImageNet. We show that MobileOne achieves state-of-the-art performance within the efficient architectures while being many times faster on mobile. Our best model obtains similar performance on ImageNet as MobileFormer while being 38x faster. Our model obtains 2.3% better top-1 accuracy on ImageNet than EfficientNet at similar latency. Furthermore, we show that our model generalizes to multiple tasks - image classification, object detection, and semantic segmentation with significant improvements in latency and accuracy as compared to existing efficient architectures when deployed on a mobile device.
*Models with * are converted from the [official repo](https://github.com/apple/ml-mobileone). The config files of these models are only for validation. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.*
*Because the [official repo.](https://github.com/apple/ml-mobileone) does not give a strategy for training and testing, the test data pipline of [RepVGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg) is used here, and the result is about 0.1 lower than that in the paper. Refer to [this issue](https://github.com/apple/ml-mobileone/issues/2).*
## How to use
The checkpoints provided are all `training-time` models. Use the reparameterize tool to switch them to more efficient `inference-time` architecture, which not only has fewer parameters but also less calculations.
### Use tool
Use provided tool to reparameterize the given model and save the checkpoint:
`${CFG_PATH}` is the config file path, `${SRC_CKPT_PATH}` is the source chenpoint file path, `${TARGET_CKPT_PATH}` is the target deploy weight file path.
Use the API `switch_to_deploy` of `MobileOne` backbone to to switch to the deploy mode. Usually called like `backbone.switch_to_deploy()` or `classificer.backbone.switch_to_deploy()`.
