Now let's try and use the trained ONNX file for inference on some manually drawn images on GIMP:
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!
  • images must be converted to 32x32 for lenet.onnx, as that is what training was done on. The training step converted the 28x28 images to 32x32 as the first thing it does before training even starts
We can try the code adapted from thenewstack.io/tutorial-using-a-pre-trained-onnx-model-for-inferencing/ at lenet/infer.py:
cd lenet
cp ~/git/LeNet-5/lenet.onnx .
wget -O 9.png https://raw.githubusercontent.com/cirosantilli/media/master/Digit_9_hand_drawn_by_Ciro_Santilli_on_GIMP_with_mouse_white_on_black.png
./infer.py 9.png
and it works pretty well! The program outputs:
9
as desired.
We can also try with images directly from Extract MNIST images.
infer_mnist.py lenet.onnx mnist_png/out/testing/1/*.png
and the accuracy is great as expected.
Perl HOWTO Updated 2025-07-16
We select for the general Equation "Schrodinger equation":
giving the full explicit partial differential equation:
Equation 1.
Schrödinger equation for a one dimensional particle
.
The corresponding time-independent Schrödinger equation for this equation is:
TCP/IP Updated 2025-07-16
Torah Updated 2025-07-16
less (Unix) Updated 2025-07-16
Mentava Updated 2025-07-16
www.mentava.com/
Mentava's software-based daily tutor gets students on track for college-level math and computer science before high school.

There are unlisted articles, also show them or only show them.