Downloads · 30 days
10
15% of all-time downloads
hf_lenet_fedavg_demo
iscyang/hf_lenet_fedavg_demo
hf_lenet_fedavg_demo is a machine learning model from iscyang. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch.
This repository is managed by the hflenetfedavgdemo scripts. It contains a LeNet classifier for [N, 1, 28, 28] grayscale images and ten output classes.
All-time downloads
67
Public
Parameters
44.4K
1.2 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors179 KB · 97%
At a glance
- Library
- pytorch
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- bfbe8634
Model card
From the Hugging Face model README
LeNet FedAvg demo
This repository is managed by the hf_lenet_fedavg_demo scripts. It
contains a LeNet classifier for [N, 1, 28, 28] grayscale images and
ten output classes.
Each client must train from the exact same main commit for a round.
Clients submit model updates through Hugging Face pull requests. The
owner computes dataset-size-weighted FedAvg and publishes a new main
commit. Do not merge a client PR directly: a PR contains one local
model, not the aggregate.
Load it with the local lenet_model.py class:
from lenet_model import LeNet
model = LeNet.from_pretrained("iscyang/hf_lenet_fedavg_demo")
This is an educational demo. It does not implement secure aggregation, differential privacy, client authentication, or poisoning defenses.
- Library
- pytorch
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026