# pCAMP: Performance Comparison of Machine Learning Packages on the Edges

arXiv: https://arxiv.org/abs/1906.01878 · HTML: https://mlsanity.com/paper/1906.01878/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

## Built on by (most cited first, 12 of 12)

- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review](https://mlsanity.com/paper/2205.01081/) (2022)
- [Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement](https://mlsanity.com/paper/2308.12264/) (2023)
- [Identifying architectural design decisions for achieving green ML serving](https://mlsanity.com/paper/2402.07585/) (2024)
- [Send Less, Save More: Energy-Efficiency Benchmark of Embedded CNN Inference vs. Data Transmission in IoT](https://mlsanity.com/paper/2510.24829/) (2025)
- [Impact of Deep Learning Libraries on Online Adaptive Lightweight Time Series Anomaly Detection](https://mlsanity.com/paper/2305.00595/) (2023)
- [Impact of Recurrent Neural Networks and Deep Learning Frameworks on Real-time Lightweight Time Series Anomaly Detection](https://mlsanity.com/paper/2407.18439/) (2024)
- [On the Sustainability of AI Inferences in the Edge](https://mlsanity.com/paper/2507.23093/) (2025)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [AI2: The next leap toward native language based and explainable machine learning framework](https://mlsanity.com/paper/2301.03391/) (2023)
- [Insights into resource utilization of code small language models serving with runtime engines and execution providers](https://mlsanity.com/paper/2412.15441/) (2024)
- [Ti-iLSTM: A TinyDL Approach for Logic-Level Anomaly Detection in Industrial Water Treatment Systems](https://mlsanity.com/paper/2605.15874/) (2026)

## Abstract (arXiv)

Machine learning has changed the computing paradigm. Products today are built with machine intelligence as a central attribute, and consumers are beginning to expect near-human interaction with the appliances they use. However, much of the deep learning revolution has been limited to the cloud. Recently, several machine learning packages based on edge devices have been announced which aim to offload the computing to the edges. However, little research has been done to evaluate these packages on the edges, making it difficult for end users to select an appropriate pair of software and hardware. In this paper, we make a performance comparison of several state-of-the-art machine learning packages on the edges, including TensorFlow, Caffe2, MXNet, PyTorch, and TensorFlow Lite. We focus on evaluating the latency, memory footprint, and energy of these tools with two popular types of neural networks on different edge devices. This evaluation not only provides a reference to select appropriate combinations of hardware and software packages for end users but also points out possible future directions to optimize packages for developers.