def main():
# prepare sample input for forwad()
train_loader = torchvision.datasets.MNIST('../data_MNIST',
train=True,
download=True,
transform=True,
target_transform=True)
epoch = 10
learning_rate = 0.5
batch_size = 100
numCls = 10
iteration = len(train_loader) / batch_size
input = (torch.squeeze(
train_loader.train_data.view(iteration, batch_size, 1, 784),
2)).type(torch.FloatTensor)
# Test NnImg2Num
net = NnImg2Num()
net.train()
print('forward output', net.forward(input[0]))
print('call output', net(input[0]))
# Test MyImg2Num
netMy = MyImg2Num()
netMy.train()
print('forward output', netMy.forward((input[0])))
print('call output', netMy((input[0])))
train_mse = np.array(train_mse)
train_accuracy = np.array(train_accuracy)
test_mse = np.array(test_mse)
test_accuracy = np.array(test_accuracy)
plt.plot(epoch_scale, train_mse, label='train mse')
plt.plot(epoch_scale, test_mse, label='test mse')
plt.xlabel('epochs')
plt.ylabel('mse')
plt.title('MyNN MSE vs Epochs')
plt.legend()
plt.show()
py_nn = NnImg2Num(train_batch, test_batch)
train_error, test_error, epoch_scale = py_nn.train(epochs)
accuracy = py_nn.test_accuracy()
print(f'accuracy on test: {accuracy}')
mse = py_nn.test_mse()
print(f'mse on test: {mse}')
train_mse, train_accuracy = train_error
test_mse, test_accuracy = test_error
train_mse = np.array(train_mse)
train_accuracy = np.array(train_accuracy)
test_mse = np.array(test_mse)
test_accuracy = np.array(test_accuracy)
from my_img2num import MyImg2Num from nn_img2num import NnImg2Num myi2n = MyImg2Num() myi2n.train() nni2n = NnImg2Num() nni2n.train()
from nn_img2num import NnImg2Num from my_img2num import MyImg2Num nn_mnist = NnImg2Num() nn_mnist.train() # my_mnist = MyImg2Num() # my_mnist.train()
import torch
from torchvision import datasets, transforms
import time
import matplotlib.pyplot as plt
from nn_img2num import NnImg2Num
# Create object for NnImg2Num class
model = NnImg2Num()
# Load test data
TestLoader = torch.utils.data.DataLoader(
datasets.MNIST(
'../data',
train=False,
transform=transforms.Compose([
transforms.ToTensor(),
#transforms.Normalize((0.1307,), (0.3801,))
])),
batch_size=1,
shuffle=True)
# Initiate error rate, operation time and epochs
eRate, opTime, epochs = [], [], []
# Train model using different epoch
for i in range(1, 10):
epoch = i * 10
startTime = time.time()
model.epoch = epoch
model.train()
opTime.append(time.time() - startTime)
import torch
import torchvision
import torchvision.transforms as transforms
from my_img2num import MyImg2num
from nn_img2num import NnImg2Num
from matplotlib import pyplot as plt
import numpy as np
import torch.nn as nn
from neural_network import NeuralNetwork as NN
#myimg2num = MyImg2num()
#myimg2num.train()
nnimg2num = NnImg2Num()
nnimg2num.train()
transform = transforms.ToTensor()
test_set = torchvision.datasets.MNIST('/tmp',
train=False,
transform=transform,
download=True)
testloader = torch.utils.data.DataLoader(test_set,
batch_size=10000,
shuffle=False)
dataiter = iter(testloader)
images, data = dataiter.next()
counter = 0
for i in range(10000):
a = nnimg2num.forward(images[i, 0, :, :])
def main():
# model_my = MyImg2Num()
model_my = NnImg2Num()
model_my.train()
print('done')
import torchvision
import torch
import torchvision.transforms as transforms
from my_img2num import MyImg2Num
from nn_img2num import NnImg2Num
device = torch.device("cuda:2" if torch.cuda.is_available() else "cpu")
print(device)
## TRAIN ON MY NETWORK
mynet = MyImg2Num()
#mynet.to(device)
mynet.train()
# TRAIN ON TORCH NETWORK
net = NnImg2Num()
#net.to(device)
net.train()