Personalize DL models on the edge.
Project description
Model Personalization on Edge
Improving the performance of DL models for individual users by re-training on a user's data on the edge.
QMNIST Dataset
Divide the datset by the writer ID.
python preprocess/filter_by_user.py --download --dataset=train
python preprocess/filter_by_user.py --download --dataset=test
The resulting user-specific datasets will be under data/QMNIST/train
and data/QMNIST/test
.
The file naming convention is w-<witer_id>.pth
.
To load the dataset of a specific writer:
import torch
from torch.utils.data import DataLoader
dataset = torch.load('data/QMNIST/train/w-<writer_id>.pth')
dataloader = DataLoader(dataset)
License
BSD 3-Clause License.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
edgify-0.0.1.tar.gz
(3.9 kB
view hashes)
Built Distribution
edgify-0.0.1-py2-none-any.whl
(5.8 kB
view hashes)