#!/usr/bin/python import pandas as pd import numpy as np import zadanie1 as z import torch import torchvision import torchvision.transforms as transforms import torch.nn as nn import torch.nn.functional as F import torch.optim as optim from sacred import Experiment from sacred.observers import FileStorageObserver from sacred.observers import MongoObserver class Net(nn.Module): def __init__(self): super().__init__() #self.conv1 = nn.Conv2d(3, 6, 5) #self.pool = nn.MaxPool2d(2, 2) #self.conv2 = nn.Conv2d(6, 16, 5) #self.fc1 = nn.Linear(16 * 5 * 5, 120) #self.fc2 = nn.Linear(20, 6) self.fc3 = nn.Linear(6, 6) def forward(self, x): #x = self.pool(F.relu(self.conv1(x))) #x = self.pool(F.relu(self.conv2(x))) #x = torch.flatten(x, 1) #x = F.relu(self.fc1(x)) #x = F.relu(self.fc2(x)) x = self.fc3(x) return x def trainNet(_run, trainloader, criterion, optimizer, net, epochs=20): for epoch in range(epochs): for i, data in enumerate(trainloader, 0): inputs, labels = data labelsX = torch.Tensor([x for x in labels]) labels = labelsX.type(torch.LongTensor) optimizer.zero_grad() outputs = net(inputs) loss = criterion(outputs, labels) print(loss[0]) _run.log_scalar("training.loss", loss) loss.backward() optimizer.step() print('Finished Training') ex = Experiment("s452627", interactive=True, save_git_info=False) ex.observers.append(FileStorageObserver('my_runs')) #ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017', db_name='sacred')) @ex.config def my_config(): epochs = 10 learning_rate = 0.001 @ex.automain def my_main(epochs, learning_rate, _run): ex.open_resource("Customers.csv", "r") train, dev, test = z.prepareData() batch_size = 4 trainlist = train.values.tolist() testlist = test.values.tolist() trainset = [[torch.Tensor(x[1:]), torch.Tensor([x[0]])] for x in trainlist] trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True, num_workers=2) testset = [[torch.Tensor(x[1:]), torch.Tensor([x[0]])] for x in testlist] testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False, num_workers=2) classes = ('male', 'female') net = Net() criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9) trainNet(_run, trainloader, criterion, optimizer, net, int(float(epochs))) PATH = './cifar_net.pth' torch.save(net.state_dict(), PATH) ex.add_artifact("cifar_net.pth") #if __name__ == '__main__': #ex.run()