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.
1 maintainer
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 details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file edgify-0.0.1.tar.gz.
File metadata
- Download URL: edgify-0.0.1.tar.gz
- Upload date:
- Size: 3.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/3.2.0 pkginfo/1.6.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.51.0 CPython/3.8.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3b3bfe83d0fa6e0107f02ad161e1afd65db833ea923069dd8c2fd9ff678490ab
|
|
| MD5 |
cada661024bc122d11ae40d616d091f1
|
|
| BLAKE2b-256 |
6ebfde34ff4aa8be25762ee1e5379c667230c2f36c54ab28d581b0c735fc8618
|
File details
Details for the file edgify-0.0.1-py2-none-any.whl.
File metadata
- Download URL: edgify-0.0.1-py2-none-any.whl
- Upload date:
- Size: 5.8 kB
- Tags: Python 2
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/3.2.0 pkginfo/1.6.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.51.0 CPython/3.8.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2ad80db5ae507a2442a83dd5538b172f2813b4382e019a59a02a231912a945e8
|
|
| MD5 |
3aa4dbd37165452eec2dd51f8140a163
|
|
| BLAKE2b-256 |
ae8b3d8dbfbc0c03882a831ba58149f6f77a782d11a5ba240dd685547d39c93f
|
