YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
SMAI A4: MLP on CIFAR-10
- kind: MLP
- widths: [3072, 64, 10]
- hidden_activation: ReLU
- output: logits (no activation), apply softmax for probabilities
- loss: cross entropy
- preprocessing: flatten 32x32x3 image to 3072, float64, divide by 255, subtract mean and divide by std from preprocessing.npz (50,000 CIFAR-10 train images)
- seed: 1088
- noise_p: 0.0
- epochs: 100
- learning_rate: 0.02
- batch_size: 64
- parameters: 197322
- final_test_accuracy: 0.4448
Weights in model.npz use the layout of our NumPy library: W{i} has shape (n_in, n_out), b{i} has shape (n_out,).
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support