train_data = data[:train_len]
train_tar = target[:train_len]
valid_data = data[train_len:train_len + valid_len]
valid_tar = target[train_len:train_len + valid_len]
test_data = data[train_len + valid_len:]
test_tar = target[train_len + valid_len:]
data = {
'X_train': train_data, # training data
'y_train': train_tar, # training labels
'X_val': valid_data, # validation data
'y_val': valid_tar # validation labels
}
model = log.LogisticClassifier(input_dim=D, hidden_dim=200, reg=0.001)
solver = solver.Solver(model, data,
update_rule='adam',
optim_config={
'learning_rate': 1e-3,
},
lr_decay=1,
num_epochs=3000, batch_size=500,
print_every=1)
solver.train()
acc = solver.check_accuracy(test_data, test_tar)
print('Test Accuracy: %f' % acc)
with open('data.pkl', 'rb') as f:
data = pickle.load(f, encoding='latin1')
print(np.shape(data[0][0:500, :]))
x_test = data[0][750:, :]
y_test = data[1][750:]
data_input = {
'X_train': data[0][0:500, :],
'y_train': data[1][0:500],
'X_val': data[0][500:750, :],
'y_val': data[1][500:750]# validation labels
}
model = logistic.LogisticClassifier(input_dim=20, reg=0.12) #lr=2
#model = logistic.LogisticClassifier(input_dim=20, hidden_dim=16, reg=0.08) # lr=0.8
solver = solver.Solver(model, data_input,
update_rule='sgd',
optim_config={
'learning_rate': 0.8,
},
lr_decay=0.98,
num_epochs=800, batch_size=40,
print_every=2000)
solver.train()
print(solver.check_accuracy(x_test, y_test, num_samples=None, batch_size=40))
#print(solver.best_params)