Star

Issue

Welcome to JS-PyTorch's Web Demo! You can set the Model Layers on the right (number of layers and hidden dimension of each layer), and choose the Model Hyperparameters in real time.

• This model was trained on the MNIST dataset, using 2000 training and 100 validation images.


• The images are handwritten digits from 0 to 9, each with a dimension of 28x28.


• The model output is a number from 0 to 9.


• The training uses the Adam Optimizer and a Cross Entropy Loss.

Training Hyperparameters

Batch Size: Learning Rate: L2 Regularization: Beta 1 (Adam): Beta 2 (Adam):

Model Layers

+ -

Train Pause Reset Clear

CPU GPU

Validation Loss:

Validation Accuracy:

Iteration:

Epoch:

Total Training Examples:

Device: