Accelerating Deep Learning Inference via Freezing.
作者： Shivaram Venkataraman , Aditya Akella , Adarsh Kumar , Arjun Balasubramanian
DOI:
关键词:
摘要: … caching at each intermediate layer and we discuss techniques to reduce the cache size and improve the cache … we see that the cache requires a mere 12.5MB of memory for ResNet-18. …
参考文章(0)