| ---
|
| library_name: numpy
|
| tags:
|
| - image-classification
|
| - cifar10
|
| datasets:
|
| - uoft-cs/cifar10
|
| ---
|
|
|
| # CIFAR-10 MLP (3072-128-10)
|
|
|
| A multi-layer perceptron for CIFAR-10 on raw pixels.
|
|
|
| - Architecture: 3072-128-10 (394,634 parameters); hidden activation `relu`, Identity output layer (logits).
|
| - Trained on the 50,000 CIFAR-10 training images with their true labels for 100 epochs: plain SGD, learning rate 0.01, batch size 64, cross-entropy loss, seed 1076.
|
| - CIFAR-10 test accuracy (10,000 images): 0.4833; final training accuracy 0.9061.
|
|
|
| ## Files
|
|
|
| - `weights.npz`: `W0, b0, W1, b1` (float64); layer `i` computes `h @ W_i + b_i` with `W_i` of shape (n_in, n_out).
|
| - `preprocessing.npz`: `mean` and `std` (3072 values each) of the training pixels after dividing by 255.
|
| - `config.json`: architecture, preprocessing, training settings and results.
|
|
|
| ## Use
|
|
|
| ```python
|
| import numpy as np
|
|
|
| w, prep = np.load("weights.npz"), np.load("preprocessing.npz")
|
| x = (images.reshape(len(images), 3072) / 255.0 - prep["mean"]) / prep["std"] # images: uint8 (n, 32, 32, 3)
|
| h = np.maximum(x @ w["W0"] + w["b0"], 0.0)
|
| logits = h @ w["W1"] + w["b1"] # classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck
|
| ```
|
|
|
