 activatedgeek/LeNet-5

 New to topics? Read the documentation here!

 Top articles  Latest articles + New article in topic

Ciro Santilli 34  Updated 2024-12-15  +Created 1970-01-01

Good packaging! Tested on Ubuntu 22.10:

git clone https://github.com/activatedgeek/LeNet-5
cd LeNet-5
git checkout 95b55a838f9d90536fd3b303cede12cf8b5da47f
virtualenv -p python3 .venv
. .venv/bin/activate

# Their requirements.txt uses >= and some == are incompatible with our Ubuntu.
pip install
  Pillow==6.2.0 \
  numpy==1.24.2 \
  onnx==1.13.1 \
  torch==2.0.0 \
  torchvision==0.15.1 \
  visdom==0.2.4 \
;

time python run.py

This throws a billion exceptions because we didn't start the visdom server, but never mind that.

The scrip does a fixed 15 epochs.

Output on P51:

real    2m10.262s
user    11m9.771s
sys     0m26.368s

The run also produces a lenet.onnx ONNX file, which is pretty neat, and allows us for example to visualize it on Netron:

Figure 1.
Netron visualization of the activatedgeek/LeNet-5 ONNX output
. From this we can see the bifurcation on the computational graph as done in the code at:
`output = self.c1(img) x = self.c2_1(output) output = self.c2_2(output) output += x output = self.c3(output)`
This doesn't seem to conform to the original LeNet-5 however?

 Read the full article