NeuralNetwork/learning_results.txt

@@ -0,0 +1,10 @@
+Epoch:  1 Train Loss: 65 Train Accuracy: 0.5754245754245755
+Epoch:  2 Train Loss: 25 Train Accuracy: 0.7457542457542458
+Epoch:  3 Train Loss: 8 Train Accuracy: 0.8431568431568431
+Epoch:  4 Train Loss: 2 Train Accuracy: 0.9010989010989011
+Epoch:  5 Train Loss: 1 Train Accuracy: 0.9335664335664335
+Epoch:  6 Train Loss: 0 Train Accuracy: 0.9545454545454546
+Epoch:  7 Train Loss: 0 Train Accuracy: 0.972027972027972
+Epoch:  8 Train Loss: 0 Train Accuracy: 0.9820179820179821
+Epoch:  9 Train Loss: 0 Train Accuracy: 0.994005994005994
+Epoch:  10 Train Loss: 0 Train Accuracy: 0.9945054945054945

NeuralNetwork/neural_network_learning.py

@@ -0,0 +1,60 @@
+import glob
+from src.torchvision_resize_dataset import combined_dataset, images_path, classes
+import src.data_model
+from torch.optim import Adam
+import torch 
+import torch.nn as nn 
+from torch.utils.data import DataLoader 
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+train_loader = DataLoader(
+    combined_dataset,   #dataset of images
+    batch_size=256,     # accuracy
+    shuffle=True    # rand order
+)
+
+model = src.data_model.DataModel(num_objects=2).to(device)
+
+#optimizer 
+optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
+#loss function
+criterion = nn.CrossEntropyLoss()
+
+num_epochs = 10
+# train_size = len(glob.glob(images_path+'*.jpg'))
+train_size = 2002
+
+go_to_accuracy = 0.0
+for epoch in range(num_epochs):
+    #training on dataset
+    model.train()
+    train_accuracy = 0.0
+    train_loss = 0.0
+    for i, (images, labels) in enumerate(train_loader):
+        if torch.cuda.is_available():
+            images = torch.Variable(images.cuda())
+            labels = torch.Variable(labels.cuda())
+        # clearing the optimizer gradients
+        optimizer.zero_grad()
+
+        outputs = model(images) # predoction
+        loss = criterion(outputs, labels)   #loss calculation
+        loss.backward()
+        optimizer.step()
+
+        train_loss += loss.cpu().data*images.size(0)
+        _, prediction = torch.max(outputs.data, 1)
+
+        train_accuracy += int(torch.sum(prediction == labels.data))
+
+    train_accuracy = train_accuracy/train_size
+    train_loss = train_loss/train_size
+
+    model.eval()
+
+    print('Epoch:  '+ str(epoch+1) +' Train Loss: '+ str(int(train_loss)) +' Train Accuracy: '+ str(train_accuracy))
+
+    if train_accuracy > go_to_accuracy:
+        go_to_accuracy= train_accuracy
+        torch.save(model.state_dict(), "best_model.pth") 

NeuralNetwork/src/data_model.py

@@ -0,0 +1,61 @@
+import torch.nn as nn 
+import torch
+
+
+class DataModel(nn.Module):
+    def __init__(self, num_objects):
+        super(DataModel, self).__init__()
+        #input (batch=256, nr of channels rgb=3 , size=244x244)
+
+        # convolution
+        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=3, stride=1, padding=1)
+        #shape (256, 12, 224x224)
+
+        # batch normalization
+        self.bn1 = nn.BatchNorm2d(num_features=12)
+        #shape (256, 12, 224x224)
+        self.reul1 = nn.ReLU()
+
+        self.pool=nn.MaxPool2d(kernel_size=2, stride=2)
+        # reduce image size by factor 2
+        # pooling window moves by 2 pixels at a time instead of 1
+        # shape (256, 12, 112x112)
+
+
+
+        self.conv2 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=3, stride=1, padding=1)
+        self.bn2 = nn.BatchNorm2d(num_features=24)
+        self.reul2 = nn.ReLU()
+        # shape (256, 24, 112x112)
+
+        self.conv3 = nn.Conv2d(in_channels=24, out_channels=48, kernel_size=3, stride=1, padding=1)
+        #shape (256, 48, 112x112)
+        self.bn3 = nn.BatchNorm2d(num_features=48)
+        #shape (256, 48, 112x112)
+        self.reul3 = nn.ReLU()
+
+        # connected layer
+        self.fc = nn.Linear(in_features=48*112*112, out_features=num_objects)
+
+    def forward(self, input):
+            output = self.conv1(input)
+            output = self.bn1(output)
+            output = self.reul1(output)
+
+            output = self.pool(output)
+            output = self.conv2(output)
+            output  = self.bn2(output)
+            output = self.reul2(output)
+            
+            output = self.conv3(output)
+            output = self.bn3(output)
+            output = self.reul3(output)
+
+            # output shape matrix (256, 48, 112x112)
+            #print(output.shape)
+            #print(self.fc.weight.shape)
+
+            output = output.view(-1, 48*112*112)
+            output = self.fc(output)
+            
+            return output

NeuralNetwork/src/torchvision_resize_dataset.py

@@ -0,0 +1,31 @@
+import glob
+import pathlib
+import torchvision.transforms as transforms
+from torchvision.datasets import ImageFolder
+from torch.utils.data import ConcatDataset
+
+# images have to be the same size for the algorithm to work
+transform = transforms.Compose([
+    transforms.Resize((224, 224)),  # Resize images to (224, 224)
+    transforms.ToTensor(),  # Convert images to tensors, 0-255 to 0-1
+    # transforms.RandomHorizontalFlip(),  # 0.5 chance to flip the image
+    transforms.Normalize([0.5,0.5,0.5], [0.5,0.5,0.5]) 
+])
+
+letters_path = 'C:/Users/wojmed/Documents/VS repositories/Inteligentny_Wozek/NeuralNetwork/src/train_images/letters'
+package_path = 'C:/Users/wojmed/Documents/VS repositories/Inteligentny_Wozek/NeuralNetwork/src/train_images/package'
+images_path = 'C:/Users/wojmed/Documents/VS repositories/Inteligentny_Wozek/NeuralNetwork/src/train_images'
+
+# # Load images from folders
+# letter_folder = ImageFolder(letters_path, transform=transform)
+# package_folder = ImageFolder(package_path, transform=transform)
+
+# Combine the both datasets into a single dataset
+#combined_dataset = ConcatDataset([letter_folder, package_folder])
+combined_dataset = ImageFolder(images_path, transform=transform)
+
+#image classes
+path=pathlib.Path(images_path)
+classes = sorted([i.name.split("/")[-1] for i in path.iterdir()])
+
+# print(classes)