We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The tradeoff between performance and inference speed is critical for practical applications. Architecture reparameterization obtains better tradeoffs and it is becoming an increasingly popular ingredient in modern convolutional neural networks. Nonetheless, its quantization performance is usually too poor to deploy (more than 20% top-1 accuracy drop on ImageNet) when INT8 inference is desired. In this paper, we dive into the underlying mechanism of this failure, where the original design inevitably enlarges quantization error. We propose a simple, robust, and effective remedy to have a quantization-friendly structure that also enjoys reparameterization benefits. Our method greatly bridges the gap between INT8 and FP32 accuracy for RepVGG. Without bells and whistles, the top-1 accuracy drop on ImageNet is reduced within 2% by standard post-training quantization. Moreover, our method also achieves similar FP32 performance as RepVGG. Extensive experiments on detection and semantic segmentation tasks verify its generalization.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2212.01593")
get_code_for_paper("2212.01593")
have("2212.01593")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2212.01593.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2212.01593)
Connect an agent — have() is free.