EdgeTune: Inference-Aware Hyperparameter Tuning
Bibliographic record
Abstract
# EdgeTune: Inference-Aware Hyperparameter Tuning The results of EdgeTune have been presented at the ACM Middleware 2022 conference. If you use this software, please cite us: ``` @inproceedings{10.1145/3528535.3533273, author = {Rocha, Isabelly and Felber, Pascal and Schiavoni, Valerio and Chen, Lydia}, title = {EdgeTune: Inference-Aware Multi-Parameter Tuning}, year = {2022}, isbn = {9781450393409}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3528535.3533273}, doi = {10.1145/3528535.3533273}, booktitle = {Proceedings of the 23rd Conference on 23rd ACM/IFIP International Middleware Conference}, pages = {1–14}, numpages = {14}, keywords = {tuning, deep neural networks, training, inference}, location = {Quebec, QC, Canada}, series = {Middleware '22} } ``` ## Install pip3 ```Shell $ sudo apt-get update $ sudo apt-get install python3-pip ``` ## Install Python dependencies - Intel (nuc) ```Shell $ pip3 install torch torchvision keras tensorflow ray[rllib] pandas tensorflow_datasets ``` - ARM (RaspberryPi) ```Shell $ git clone https://github.com/Ben-Faessler/Python3-Wheels.git $ sudo pip3 install Python3-Wheels/pytorch/torch-1.5.0a0+4ff3872-cp37-cp37m-linux_armv7l.whl $ sudo pip3 install Python3-Wheels/torchvision/torchvision-0.6.0a0+b68adcf-cp37-cp37m-linux_armv7l.whl ``` - Jetson Nano ```Shell $ wget https://nvidia.box.com/shared/static/wa34qwrwtk9njtyarwt5nvo6imenfy26.whl -O torch-1.7.0-cp36-cp36m-linux_aarch64.whl $ sudo apt-get install python3-pip libopenblas-base libopenmpi-dev $ pip3 install Cython $ pip3 install numpy torch-1.7.0-cp36-cp36m-linux_aarch64.whl $ sudo apt-get install libjpeg-dev zlib1g-dev $ git clone --branch v0.8.1 https://github.com/pytorch/vision torchvision $ cd torchvision $ export BUILD_VERSION=0.8.1 $ sudo python3 setup.py install ``` ## Install cpupower (for frequency scaling) ```Shell $ sudo apt-get install linux-cpupower $ cpufreq-info # get cpu frequency information $ cpufreq-set -u min -d max # set cpu frequency ``` ## Power Measurements Setup - InfluxDB ```Shell $ sudo apt install influxdb $ service influxdb start $ influx $ CREATE DATABASE power ``` - PowerSpy Power ```Shell $ pip install influxdb $ python powerspy.py MAC ``` - POE Power ```Shell $ apt-get install python-bluez bluez $ hcitool scan $ hcitool dev $ systemctl restart bluetooth.service $ pip3 install influxdb $ python3 poe_power.py -p PORT ``` - RAPL ```Shell $ sudo chmod -R a+r /sys/class/powercap/intel-rapl ``` ## Change rapl permissions ```Shell sudo chmod -R a+r /sys/class/powercap/intel-rapl ``` ## Install cuda dependencies ```Shell $ wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin $ sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600 $ sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/7fa2af80.pub $ sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /" $ sudo apt-get update $ $ sudo apt install nvidia-cuda-toolkit
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.018 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.032 | 0.013 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".