def main():
# get arguments
train_size, epochs, learning_rate, path = functions.read_argv()
# get data
train_data = functions.read_gz_idx(path + 'train-images-idx3-ubyte.gz')
train_label = functions.read_gz_idx(path + 'train-labels-idx1-ubyte.gz')
test_data = functions.read_gz_idx(path + 't10k-images-idx3-ubyte.gz')
test_label = functions.read_gz_idx(path + 't10k-labels-idx1-ubyte.gz')
train_data, train_label, test_data, test_label = mnist_data_preprocess(
train_data, train_label, test_data, test_label, train_size)
# start training
model = vanilla_perceptron(len(train_data[0]), learning_rate, epochs)
model.train(train_data, train_label)
# model.print_weights()
# classify
prediction = model.classify(train_data)
f1, p, r = functions.f1_score(prediction, train_label)
print ' > train f1 score: %.3f\t' % (f1)
# print ' > train f1 score: %.3f\tprecision: %.3f\trecall: %.3f' % (f1, p, r)
prediction = model.classify(test_data)
f1, p, r = functions.f1_score(prediction, test_label)
print ' > test f1 score: %.3f\t' % (f1)
def main():
# get arguments
regularization, feature_type, path = functions.read_argv()
epochs, mini_batch_size = 200, 10000
stop_criteria = 0.0005
# get data
train_data = functions.read_gz_idx(path+'train-images-idx3-ubyte.gz')
train_label = functions.read_gz_idx(path+'train-labels-idx1-ubyte.gz')
test_data = functions.read_gz_idx(path+'t10k-images-idx3-ubyte.gz')
test_label = functions.read_gz_idx(path+'t10k-labels-idx1-ubyte.gz')
# data preprocessing
train_data, train_label, test_data, test_label = data_preprocess(train_data, train_label, test_data, test_label, feature_type)
# model initialization
model = StochasticGradientDescent(len(train_data[0]), regularization, mini_batch_size)
# initialize list for plotting
accuracy_train = []
accuracy_test = []
# start training
prev_loss = 0 # for stopping criteria
epoch = epochs # for plotting
for e in range(epochs):
# shuffle training data if batch
if mini_batch_size == len(train_data):
train_data, train_label = functions.unison_shuffle(train_data, train_label)
# model fitting
loss = model.fit(train_data, train_label, 0)
# test the accuracy
acc_train = functions.accuracy(model.classify(train_data), train_label)/100
acc_test = functions.accuracy(model.classify(test_data), test_label)/100
# record for plotting
accuracy_train.append(acc_train)
accuracy_test.append(acc_test)
# log
print ("epoch {0:3d}:\t Train loss: {1:8.4f},\t Train acc: {2:8.4f}, \tTest acc: {3:8.4f}".format(
e+1, loss, acc_train, acc_test))
# stopping criteria
if np.absolute(prev_loss-loss)<stop_criteria:
epoch = e+1
break
prev_loss = loss
print ('End of Train & Test')
print ('Plotting ... ')
# plot to graph
if regularization: title = 'GD Regularize '+feature_type
else: title = 'GD '+feature_type
functions.plot(title, [e for e in range(1, epoch+1)], accuracy_train, accuracy_test)
print ("End Of The Program")