def main(phase):
# load train_data, valid_data, test_data
train_data, valid_data, test_data = load_data()
# pdb.set_trace()
# construct the network
model = network2.Network([784, 20, 10])
# train the network using SGD
if phase == "train":
result = model.SGD(training_data=train_data,
epochs=100,
mini_batch_size=128,
eta=1e-3,
lmbda=0.0,
evaluation_data=valid_data,
monitor_evaluation_cost=True,
monitor_evaluation_accuracy=True,
monitor_training_cost=True,
monitor_training_accuracy=True)
show_metric_plot(result[2], result[0], 100, 'Training Error',
'Validation Error', 'Loss', 'Loss v/s Epochs')
evaluation_accuracy = list(map(lambda x: x * 100 / 10000, result[1]))
training_accuracy = list(map(lambda x: x * 100 / 3000, result[3]))
show_metric_plot(training_accuracy, evaluation_accuracy, 100,
'Training Accuracy', 'Validation Accuracy',
'Accuracy %', 'Accuracy v/s Epochs')
model.save('train_model')
if phase == "test":
net = network2.load('train_model')
print('Accuracy for Test Data:{}%'.format(
net.accuracy(test_data) / 100))
def test():
train_data, valid_data, test_data = load_data()
print("length of test data:",len(test_data[0]))
net=network2.load('Saved_Weights')
accuracy = net.accuracy(test_data)
print("Test Accuracy",accuracy/len(test_data[0]))
print("Test Accuracy: {} / {}".format(accuracy, len(test_data[0])))
def test_model():
# load train_data, valid_data, test_data.
train_data, valid_data, test_data = load_data()
# load the model.
model = network2.load('../../sgd_model.json')
accuracy = model.accuracy(test_data, convert=False)
total_cost = model.total_cost(test_data, 0.0, convert=True)
print('Accuracy: {}'.format(accuracy))
print('Total Cost: {}'.format(total_cost))
def main_test():
# load train_data, valid_data, test_data
train_data, valid_data, test_data = load_data()
# construct the network
#model = network2.Network([784, 20, 10])
model = network2.load('saver')
#test the network using SGD
test_cost = model.total_cost(test_data, lmbda = 0.0, convert=True)
test_accuracy = model.accuracy(test_data, convert=False)
print('Test cost : ', test_cost)
print('Test Accuracy : ', test_accuracy)
def __init__(self):
super(Root, self).__init__()
self.title("Recognize handwritten digits")
self.minsize(500, 400)
self.labelFrame = LabelFrame(self, text="Otwórz plik")
self.labelFrame.grid(column=1, row=1, padx=20, pady=20)
self.button1()
self.button2()
self.label_file = ttk.Label(self.labelFrame, text="")
self.label_result = ttk.Label(self.labelFrame, text="")
self.fig = Figure(figsize=(5, 5), dpi=100)
self.net = network2.load('../data/network_params')
def test_network(file_name):
print('testing network')
print('loading saved file: ', file_name)
model = network2.load(file_name)
# load train_data, valid_data, test_data
train_data, valid_data, test_data = load_data()
num_correct = 0
for i in range(len(test_data[0])):
prediction = np.argmax(model.feedforward(test_data[0][i]))
if prediction == test_data[1][i]:
num_correct += 1
test_accuracy = num_correct / len(test_data[0])
print("Test accuracy: " + str(test_accuracy))
def test():
# load train_data, valid_data, test_data
test_data = load_data()[2]
#loading the neural Network
model = network2.load('NeuralNet_new_fc.csv')
test_cost = model.total_cost(test_data, lmbda=0.0, convert=True)
test_accuracy = model.accuracy(test_data)
'''result = []
for i in range(len(test_data[0])):
result.append(network2.vectorized_result(np.argmax(model.feedforward(test_data[0][i]))))
df = pd.DataFrame(list(map(np.ravel, result)))
df.to_csv('Arsingh3_hw02b_Prediction_Submission.csv')'''
#result = model.feedforward()
print('Test Error: {}'.format(test_cost))
print('Test accuracy: {}'.format(test_accuracy))
def main():
# load train_data, valid_data, test_data
train_data, valid_data, test_data = load_data()
# construct the network
model = network2.Network([784, 32, 10])
# train the network using SGD
validation_loss , validation_accuracy, training_loss, training_accuracy = model.SGD(
training_data=train_data,
epochs=75,
mini_batch_size=64,
eta=0.002,
lmbda = 0.0,
evaluation_data=valid_data,
monitor_evaluation_cost=True,
monitor_evaluation_accuracy=True,
monitor_training_cost=True,
monitor_training_accuracy=True)
model.save("model0.json")
model = network2.load("model0.json")
predictions , prob, vector_base = predict(test_data, model)
plot_learning_curve(validation_loss, training_loss, validation_accuracy, training_accuracy)
csvfile = open('predictions.csv','w', newline='')
obj = csv.writer(csvfile)
obj.writerows(predictions)
csvfile.close()
csvfile = open('raw.csv','w', newline='')
obj1 = csv.writer(csvfile)
obj1.writerows(prob)
csvfile.close()
test_accuracy = 0;
for x, y in zip(vector_base, test_data[1]):
if x == y:
test_accuracy += 1
print("The accuracy on test set is: " , test_accuracy)
def test_accuracy():
train_data, valid_data, test_data = load_data()
loaded_model = network2.load('final_model.json')
print(loaded_model.accuracy(test_data) / len(test_data[0]))
def test():
train_data, valid_data, test_data = load_data()
model = network2.load("weights.json")
print("Accuracy on test data: ", model.accuracy(test_data) / 100)
