/LeNet-5

PyTorch implementation of LeNet-5 with live visualization

Primary LanguagePython

LeNet-5

This implements a slightly modified LeNet-5 [LeCun et al., 1998a] and achieves an accuracy of ~99% on the MNIST dataset.

Epoch Train Loss visualization

Setup

Install all dependencies using the following command

$ pip install -r requirements.txt

Usage

Start the visdom server for visualization

$ python -m visdom.server

Start the training procedure

$ python run.py

See epoch train loss live graph at http://localhost:8097.

References

[1] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based learning applied to document recognition." Proceedings of the IEEE, 86(11):2278-2324, November 1998.