80 lines
2.3 KiB
Python
80 lines
2.3 KiB
Python
import torch
|
|
import cv2
|
|
import torchvision
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
import torchvision.transforms as transforms
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
import torch.optim as optim
|
|
from PIL import Image
|
|
|
|
|
|
transform = transforms.Compose(
|
|
[transforms.ToTensor(),
|
|
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
|
|
|
|
|
|
class Net(nn.Module):
|
|
def __init__(self):
|
|
super(Net, self).__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 * 71 * 71, 120)
|
|
self.fc2 = nn.Linear(120, 84)
|
|
self.fc3 = nn.Linear(84, 4)
|
|
|
|
def forward(self, x):
|
|
x = self.pool(F.relu(self.conv1(x)))
|
|
x = self.pool(F.relu(self.conv2(x)))
|
|
x = x.view(x.size(0), 16 * 71 * 71)
|
|
x = F.relu(self.fc1(x))
|
|
x = F.relu(self.fc2(x))
|
|
x = self.fc3(x)
|
|
return x
|
|
|
|
|
|
def train():
|
|
net = Net()
|
|
trainset = torchvision.datasets.ImageFolder(
|
|
root='./resources/zbior_uczacy', transform=transform)
|
|
trainloader = torch.utils.data.DataLoader(
|
|
trainset, batch_size=2, shuffle=True, num_workers=2)
|
|
|
|
classes = ('glass', 'metal', 'paper', 'plastic')
|
|
criterion = nn.CrossEntropyLoss()
|
|
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
|
|
|
|
for epoch in range(10):
|
|
running_loss = 0.0
|
|
for i, data in enumerate(trainloader, 0):
|
|
inputs, labels = data
|
|
optimizer.zero_grad()
|
|
outputs = net(inputs)
|
|
loss = criterion(outputs, labels)
|
|
loss.backward()
|
|
optimizer.step()
|
|
running_loss += loss.item()
|
|
if i:
|
|
print('[%d, %5d] loss: %.3f' %
|
|
(epoch + 1, i + 1, running_loss))
|
|
running_loss = 0.0
|
|
|
|
print('Finished Training')
|
|
PATH = './wytrenowaned.pth'
|
|
torch.save(net.state_dict(), PATH)
|
|
|
|
|
|
def predict(img_path):
|
|
net = Net()
|
|
PATH = './wytrenowaned.pth'
|
|
img = Image.open(img_path)
|
|
pil_to_tensor = transforms.ToTensor()(img).unsqueeze_(0)
|
|
classes = ('glass', 'metal', 'paper', 'plastic')
|
|
net.load_state_dict(torch.load(PATH))
|
|
net.eval()
|
|
outputs = net(pil_to_tensor)
|
|
return classes[torch.max(outputs, 1)[1]]
|
|
|