Good packaging! Tested on Ubuntu 22.10:
This throws a billion exceptions because we didn't start the visdom server, but never mind that.
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.pyThe scrip does a fixed 15 epochs.
Output on P51:
real 2m10.262s
user 11m9.771s
sys 0m26.368sThe run also produces a
lenet.onnx ONNX file, which is pretty neat, and allows us for example to visualize it on Netron:
output = self.c1(img)
x = self.c2_1(output)
output = self.c2_2(output)
output += x
output = self.c3(output)Note that the images must be drawn with white on black. If you use black on white, it the accuracy becomes terrible. This is a good very example of brittleness in AI systems!
Number 9 drawn with mouse on GIMP by Ciro Santilli (2023)
We can try the code adapted from thenewstack.io/tutorial-using-a-pre-trained-onnx-model-for-inferencing/ at python/onnx_cheat/infer_mnist.py:
and it works pretty well! The protram outputs:
as desired.
cd python/onnx_cheat
./infer_mnist.py lenet.onnx infer_mnist_9.png9We can also try with images directly from Extract MNIST images.
and the accuracy is great as expected.
for f in /home/ciro/git/mnist_png/out/testing/1/*.png; do echo $f; infer.py $f ; doneBy default, the setup runs on CPU only, not GPU, as could be seen by running htop. But by the magic of PyTorch, modifying the program to run on the GPU is trivial:
and leads to a faster runtime, with less
cat << EOF | patch
diff --git a/run.py b/run.py
index 104d363..20072d1 100644
--- a/run.py
+++ b/run.py
@@ -24,7 +24,8 @@ data_test = MNIST('./data/mnist',
data_train_loader = DataLoader(data_train, batch_size=256, shuffle=True, num_workers=8)
data_test_loader = DataLoader(data_test, batch_size=1024, num_workers=8)
-net = LeNet5()
+device = 'cuda'
+net = LeNet5().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=2e-3)
@@ -43,6 +44,8 @@ def train(epoch):
net.train()
loss_list, batch_list = [], []
for i, (images, labels) in enumerate(data_train_loader):
+ labels = labels.to(device)
+ images = images.to(device)
optimizer.zero_grad()
output = net(images)
@@ -71,6 +74,8 @@ def test():
total_correct = 0
avg_loss = 0.0
for i, (images, labels) in enumerate(data_test_loader):
+ labels = labels.to(device)
+ images = images.to(device)
output = net(images)
avg_loss += criterion(output, labels).sum()
pred = output.detach().max(1)[1]
@@ -84,7 +89,7 @@ def train_and_test(epoch):
train(epoch)
test()
- dummy_input = torch.randn(1, 1, 32, 32, requires_grad=True)
+ dummy_input = torch.randn(1, 1, 32, 32, requires_grad=True).to(device)
torch.onnx.export(net, dummy_input, "lenet.onnx")
onnx_model = onnx.load("lenet.onnx")
EOFuser as now we are spending more time on the GPU than CPU:
real 1m27.829s
user 4m37.266s
sys 0m27.562s
Articles by others on the same topic
There are currently no matching articles.