이미지 유사성 비교를 위해 대비 손실을 사용하는 Siamese 네트워크 탐색

def copy_files(source_folder,files_list,des):for file in files_list:source_file=os.path.join(source_folder,file)des_file=os.path.join(des,file)shutil.copy2(source_file,des_file)print(f"Copied {file} to {des}")return def move_files(source_folder,des):files_list=os.listdir(source_folder)for file in files_list:source_file=os.path.join(source_folder,file)des_file=os.path.join(des,file)shutil.move(source_file,des_file)print(f"Copied {file} to {des}")return def rename_file(file_path,new_name):directory=os.path.dirname(file_path)new_file_path=os.path.join(directory,new_name)os.rename(file_path,new_file_path)print(f"File renamed to {new_file_path}")returnfolder_path=r"C:\Users\sri.karan\Downloads\images1\Images\*"op_path_similar=r"C:\Users\sri.karan\Downloads\images1\Images\similar_all_images"tmp=r"C:\Users\sri.karan\Downloads\images1\Images\tmp"op_path_dissimilar=r"C:\Users\sri.karan\Downloads\images1\Images\dissimilar_all_images"folders_list=glob.glob(folder_path)folders_list=list(set(folders_list).difference(set(['C:\\Users\\sri.karan\\Downloads\\images1\\Images\\similar_all_images','C:\\Users\\sri.karan\\Downloads\\images1\\Images\\tmp','C:\\Users\\sri.karan\\Downloads\\images1\\Images\\dissimilar_all_images'])))l,g=0,0random.shuffle(folders_list)for i in glob.glob(folder_path):if i in ['C:\\Users\\sri.karan\\Downloads\\images1\\Images\\similar_all_images','C:\\Users\\sri.karan\\Downloads\\images1\\Images\\tmp','C:\\Users\\sri.karan\\Downloads\\images1\\Images\\dissimilar_all_images']:continuefile_name=i.split('\\')[-1].split("-")[1]picked_files=pick_random_files(i,6)copy_files(i,picked_files,tmp)for m in range(3):rename_file(os.path.join(tmp,picked_files[m*2]),"similar_"+str(g)+"_first.jpg")rename_file(os.path.join(tmp,picked_files[m*2+1]),"similar_"+str(g)+"_second.jpg")g+=1move_files(tmp,op_path_similar)choice_one,choice_two=random.choice(range(len(folders_list))),random.choice(range(len(folders_list)))picked_dissimilar_one=pick_random_files(folders_list[choice_one],3)picked_dissimilar_two=pick_random_files(folders_list[choice_two],3)copy_files(folders_list[choice_one],picked_dissimilar_one,tmp)copy_files(folders_list[choice_two],picked_dissimilar_two,tmp)picked_files_dissimilar=picked_dissimilar_one+picked_dissimilar_twofor m in range(3):rename_file(os.path.join(tmp,picked_files_dissimilar[m]),"dissimilar_"+str(l)+"_first.jpg")rename_file(os.path.join(tmp,picked_files_dissimilar[m+3]),"dissimilar_"+str(l)+"_second.jpg")l+=1move_files(tmp,op_path_dissimilar)

import torchimport torch.nn as nnimport torch.optim as optimfrom torch.utils.data import DataLoaderfrom PIL import Imageimport numpy as npimport randomfrom torch.utils.data import DataLoader, Datasetimport torchimport torch.nn as nnfrom torch import optimimport torch.nn.functional as Fclass ImagePairDataset(torch.utils.data.Dataset):def __init__(self, root_dir):self.root_dir = root_dirself.transform = T.Compose([# We first resize the input image to 256x256 and then we take center crop.transforms.Resize((256,256)), transforms.ToTensor()])self.image_pairs = self.load_image_pairs()def __len__(self):return len(self.image_pairs)def __getitem__(self, idx):image1_path, image2_path, label = self.image_pairs[idx]image1 = Image.open(image1_path).convert("RGB")image2 = Image.open(image2_path).convert("RGB")# Convert the tensor to a PIL image# image1 = functional.to_pil_image(image1)# image2 = functional.to_pil_image(image2)image1 = self.transform(image1)image2 = self.transform(image2)# image1 = torch.clamp(image1, 0, 1)# image2 = torch.clamp(image2, 0, 1)return image1, image2, labeldef load_image_pairs(self):image_pairs = []# Assume the directory structure is as follows:# root_dir# ├── similar# │ ├── similar_image1.jpg# │ ├── similar_image2.jpg# │ └── ...# └── dissimilar# ├── dissimilar_image1.jpg# ├── dissimilar_image2.jpg# └── ...similar_dir = os.path.join(self.root_dir, "similar_all_images")dissimilar_dir = os.path.join(self.root_dir, "dissimilar_all_images")# Load similar image pairs with label 1similar_images = os.listdir(similar_dir)for i in range(len(similar_images) // 2):image1_path = os.path.join(similar_dir, f"similar_{i}_first.jpg")image2_path = os.path.join(similar_dir, f"similar_{i}_second.jpg")image_pairs.append((image1_path, image2_path, 0))# Load dissimilar image pairs with label 0dissimilar_images = os.listdir(dissimilar_dir)for i in range(len(dissimilar_images) // 2):image1_path = os.path.join(dissimilar_dir, f"dissimilar_{i}_first.jpg")image2_path = os.path.join(dissimilar_dir, f"dissimilar_{i}_second.jpg")image_pairs.append((image1_path, image2_path, 1))return image_pairsdataset = ImagePairDataset(r"/home/niq/hcsr2001/data/image_similarity")train_size = int(0.8 * len(dataset))test_size = len(dataset) - train_sizetrain_dataset, test_dataset = torch.utils.data.random_split(dataset, [train_size, test_size])batch_size = 32train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

#create the Siamese Neural Networkclass SiameseNetwork(nn.Module):def __init__(self):super(SiameseNetwork, self).__init__()# Setting up the Sequential of CNN Layers# self.cnn1 = nn.Sequential(# nn.Conv2d(3, 256, kernel_size=11,stride=4),# nn.ReLU(inplace=True),# nn.MaxPool2d(3, stride=2),# nn.Conv2d(256, 256, kernel_size=5, stride=1),# nn.ReLU(inplace=True),# nn.MaxPool2d(2, stride=2),# nn.Conv2d(256, 384, kernel_size=3,stride=1),# nn.ReLU(inplace=True)# )self.cnn1=nn.Conv2d(3, 256, kernel_size=11,stride=4)self.relu = nn.ReLU()self.maxpool1=nn.MaxPool2d(3, stride=2)self.cnn2=nn.Conv2d(256, 256, kernel_size=5,stride=1)self.maxpool2=nn.MaxPool2d(2, stride=2)self.cnn3=nn.Conv2d(256, 384, kernel_size=3,stride=1)self.fc1 =nn.Linear(46464, 1024)self.fc2=nn.Linear(1024, 256)self.fc3=nn.Linear(256, 1)# Setting up the Fully Connected Layers# self.fc1 = nn.Sequential(# nn.Linear(384, 1024),# nn.ReLU(inplace=True),# nn.Linear(1024, 32*46464),# nn.ReLU(inplace=True),# nn.Linear(32*46464,1)# )def forward_once(self, x):# This function will be called for both images# Its output is used to determine the similiarity# output = self.cnn1(x)# print(output.view(output.size()[0], -1).shape)# output = output.view(output.size()[0], -1)# output = self.fc1(output)# print(x.shape)output= self.cnn1(x)# print(output.shape)output=self.relu(output)# print(output.shape)output=self.maxpool1(output)# print(output.shape)output= self.cnn2(output)# print(output.shape)output=self.relu(output)# print(output.shape)output=self.maxpool2(output)# print(output.shape)output= self.cnn3(output)output=self.relu(output)# print(output.shape)output=output.view(output.size()[0], -1)# print(output.shape)output=self.fc1(output)# print(output.shape)output=self.fc2(output)# print(output.shape)output=self.fc3(output)return outputdef forward(self, input1, input2):# In this function we pass in both images and obtain both vectors# which are returnedoutput1 = self.forward_once(input1)output2 = self.forward_once(input2)return output1, output2

class ContrastiveLoss(torch.nn.Module):def __init__(self, margin=2.0):super(ContrastiveLoss, self).__init__()self.margin = margindef forward(self, output1, output2, label):# Calculate the euclidean distance and calculate the contrastive losseuclidean_distance = F.pairwise_distance(output1, output2, keepdim = True)loss_contrastive = torch.mean((1-label) * torch.pow(euclidean_distance, 2) +(label) * torch.pow(torch.clamp(self.margin - euclidean_distance, min=0.0), 2))return loss_contrastivenet = SiameseNetwork().cuda()criterion = ContrastiveLoss()optimizer = optim.Adam(net.parameters(), lr = 0.0005 )

counter = []loss_history = [] iteration_number= 0# Iterate throught the epochsfor epoch in range(100):# Iterate over batchesfor i, (img0, img1, label) in enumerate(train_loader, 0):# Send the images and labels to CUDAimg0, img1, label = img0.cuda(), img1.cuda(), label.cuda()# Zero the gradientsoptimizer.zero_grad()# Pass in the two images into the network and obtain two outputsoutput1, output2 = net(img0, img1)# Pass the outputs of the networks and label into the loss functionloss_contrastive = criterion(output1, output2, label)# Calculate the backpropagationloss_contrastive.backward()# Optimizeoptimizer.step()# Every 10 batches print out the lossif i % 10 == 0 :print(f"Epoch number {epoch}\n Current loss {loss_contrastive.item()}\n")iteration_number += 10counter.append(iteration_number)loss_history.append(loss_contrastive.item())show_plot(counter, loss_history)

test_loader_one = DataLoader(test_dataset, batch_size=1, shuffle=False)dataiter = iter(test_loader_one)x0, _, _ = next(dataiter)for i in range(5):# Iterate over 5 images and test them with the first image (x0)_, x1, label2 = next(dataiter)# Concatenate the two images togetherconcatenated = torch.cat((x0, x1), 0)output1, output2 = net(x0.cuda(), x1.cuda())euclidean_distance = F.pairwise_distance(output1, output2)imshow(torchvision.utils.make_grid(concatenated), f'Dissimilarity: {euclidean_distance.item():.2f}')view raweval.py hosted with ❤ by GitHub