This demo trains a convolutional neural network to classify MNIST digits dataset. The computation is performed in the web browser using GPU (WebGPU / WebGL), with training-loop implementation by Python.
Iterations | Training loss | Test loss | Test accuracy |
---|---|---|---|
- | - | - | - |
Input | ![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Prediction | - | - | - | - | - | - | - | - | - | - |
If both are checked, WebGPU is first tried. If the browser does not support it, WebGL is tried.