156 lines
4.6 KiB
Python
156 lines
4.6 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))])
|
|
|
|
|
|
# def imshow(img):
|
|
# img = img / 2 + 0.5
|
|
# npimg = img.numpy()
|
|
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
|
|
# plt.show()
|
|
|
|
|
|
# dataiter = iter(trainloader)
|
|
# images, labels = dataiter.next()
|
|
|
|
# # show images
|
|
# imshow(torchvision.utils.make_grid(images))
|
|
# # print labels
|
|
# print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
|
|
|
|
|
|
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, 10)
|
|
|
|
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():
|
|
trainset = torchvision.datasets.ImageFolder(
|
|
root='./resources/zbior_uczacy', transform=transform)
|
|
trainloader = torch.utils.data.DataLoader(
|
|
trainset, batch_size=1, 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): # loop over the dataset multiple times
|
|
print("siema")
|
|
running_loss = 0.0
|
|
for i, data in enumerate(trainloader, 0):
|
|
# get the inputs; data is a list of [inputs, labels]
|
|
inputs, labels = data
|
|
|
|
# zero the parameter gradients
|
|
optimizer.zero_grad()
|
|
|
|
# forward + backward + optimize
|
|
outputs = net(inputs)
|
|
loss = criterion(outputs, labels)
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
# print statistics
|
|
running_loss += loss.item()
|
|
if i: # print every 2000 mini-batches
|
|
print('[%d, %5d] loss: %.3f' %
|
|
(epoch + 1, i + 1, running_loss))
|
|
running_loss = 0.0
|
|
print("kyrw")
|
|
|
|
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)
|
|
if(pil_to_tensor.shape[1] == 1):
|
|
print(img_path)
|
|
classes = ('glass', 'metal', 'paper', 'plastic')
|
|
# testset = torchvision.datasets.ImageFolder(
|
|
# root='./resources/smieci', transform=transform)
|
|
# testloader = torch.utils.data.DataLoader(
|
|
# testset, batch_size=4, shuffle=True, num_workers=2)
|
|
# dataiter = iter(testloader)
|
|
# images, labels = dataiter.next()
|
|
|
|
|
|
# print images
|
|
# imshow(torchvision.utils.make_grid(images))
|
|
# print('GroundTruth: ', ' '.join('%5s' %
|
|
# classes[labels[j]] for j in range(4)))
|
|
# print('---')
|
|
# print(images)
|
|
# print('---')
|
|
net.load_state_dict(torch.load(PATH))
|
|
outputs = net(pil_to_tensor)
|
|
return classes[torch.max(outputs, 1)[1]]
|
|
|
|
# print(classes[torch.max(outputs, 1)[1]])
|
|
# print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
|
|
# for j in range(1)))
|
|
|
|
# correct = 0
|
|
# total = 0
|
|
# with torch.no_grad():
|
|
# for data in testloader:
|
|
# images, labels = data
|
|
# outputs = net(images)
|
|
# _, predicted = torch.max(outputs.data, 1)
|
|
# total += labels.size(0)
|
|
# correct += (predicted == labels).sum().item()
|
|
|
|
# print('Accuracy of the network on the test images: %d %%' % (
|
|
# 100 * correct / total))
|
|
|
|
# class_correct = list(0. for i in range(4))
|
|
# class_total = list(0. for i in range(4))
|
|
# with torch.no_grad():
|
|
# for data in testloader:
|
|
# images, labels = data
|
|
# outputs = net(images)
|
|
# _, predicted = torch.max(outputs, 1)
|
|
# c = (predicted == labels).squeeze()
|
|
# for i in range(3):
|
|
# label = labels[i]
|
|
# print(labels)
|
|
# class_correct[label] += c[i].item()
|
|
# class_total[label] += 1
|
|
|
|
|
|
# for i in range(4):
|
|
# print('Accuracy of %5s : %2d %%' % (
|
|
# classes[i], 100 * class_correct[i] / class_total[i]))
|
|
# train()
|