In [ ]:

    

import numpy as np

from Solver import Solver
from data_utils.data import get_CIFAR10_data

data = get_CIFAR10_data()
for k, v in data.iteritems():
  print '%s: ' % k, v.shape
from classifiers.cnn import ThreeLayerConvNet
num_train = 100
small_data = {
  'X_train': data['X_train'][:num_train],
  'y_train': data['y_train'][:num_train],
  'X_val': data['X_val'],
  'y_val': data['y_val'],
}

model = ThreeLayerConvNet(weight_scale=1e-2)

solver = Solver(model, small_data,
                num_epochs=10, batch_size=50,
                update_rule='adam',
                optim_config={
                  'learning_rate': 1e-3,
                },
                verbose=True, print_every=1)
solver.train()


import matplotlib.pyplot as plt
plt.subplot(2, 1, 1)
plt.plot(solver.loss_history, 'o')
plt.xlabel('iteration')
plt.ylabel('loss')

plt.subplot(2, 1, 2)
plt.plot(solver.train_acc_history, '-o')
plt.plot(solver.val_acc_history, '-o')
plt.legend(['train', 'val'], loc='upper left')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.show()


    

    




X_val:  (1000, 3, 32, 32)
X_train:  (49000, 3, 32, 32)
X_test:  (1000, 3, 32, 32)
y_val:  (1000,)
y_train:  (49000,)
y_test:  (1000,)
(Iteration 1 / 20) loss: 2.316170
(Epoch 0 / 10) train acc: 0.160000; val_acc: 0.119000
(Iteration 2 / 20) loss: 5.245447

In [ ]: