YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
SMAI Assignment 4 - MLP
CIFAR-10, architecture 3072-256-128-10, hidden activation ReLU, cross-entropy loss, SGD lr 0.05, batch size 64, 100 epochs, true labels (p = 0).
Preprocessing: flatten 32x32x3 to 3072, divide by 255, standardise with the mean and std of the 50,000 train images (stored in the .npz as mean, std).
Weights: W{i} has shape (n_in, n_out), b{i} (n_out,).
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support