Erlemar

Erlemar

import numpy as np

class TwoLayerNet(object):
	"""
	A two-layer fully-connected neural network. The net has an input dimension of
	N, a hidden layer dimension of H, and performs classification over C classes.
	We train the network with a softmax loss function and L2 regularization on the
	weight matrices. The network uses a ReLU nonlinearity after the first fully
	connected layer.

Erlemar

Step 0. Validation accuracy: 0.9166666666666666. Test accuracy: 0.6035.
Step 1. Validation accuracy: 1.0. Test accuracy: 0.6405.
Step 2. Validation accuracy: 1.0. Test accuracy: 0.6597.
Step 3. Validation accuracy: 1.0. Test accuracy: 0.6626.
Step 4. Validation accuracy: 1.0. Test accuracy: 0.6408.
Step 5. Validation accuracy: 1.0. Test accuracy: 0.612.
Step 6. Validation accuracy: 1.0. Test accuracy: 0.6077.
Step 7. Validation accuracy: 1.0. Test accuracy: 0.6182.
Step 8. Validation accuracy: 1.0. Test accuracy: 0.6771.
Step 9. Validation accuracy: 1.0. Test accuracy: 0.6725.

Erlemar