smai-a4-mlp

MLP trained on CIFAR-10 for SMAI Assignment 4 (Q1, Section 1.4/1.5).

• Architecture: 3072 -> 256 (ReLU) -> 10 (logits)
• Initialisation: normal init, variance 2/n_in, biases 0
• Training: SGD, lr 0.02, batch size 64, 100 epochs, true labels, seed 1146
• Preprocessing: flatten the 32x32x3 image (HWC order) to 3072 values, divide by 255, standardise with mean/std from preprocessing.npz (computed on the 50,000 training images)
• Files: model.npz (W0, b0, W1, b1; W has shape n_in x n_out), preprocessing.npz, config.json

Load with the NumPy Model.load_from("model.npz") of mlp.ipynb (activation ReLU).