Learn practical skills, build real-world projects, and advance your career
Created 3 years ago
%matplotlib inline
import torchvision
import torchvision.datasets as dset
import torchvision.transforms as transforms
from torch.utils.data import DataLoader,Dataset
import matplotlib.pyplot as plt
import torchvision.utils
import numpy as np
import random
from PIL import Image
import torch
from torch.autograd import Variable
import PIL.ImageOps
import torch.nn as nn
from torch import optim
import torch.nn.functional as F
!git clone https://github.com/harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch.git
!cd Facial-Similarity-with-Siamese-Networks-in-Pytorch
Cloning into 'Facial-Similarity-with-Siamese-Networks-in-Pytorch'...
remote: Enumerating objects: 18, done.
remote: Counting objects: 100% (18/18), done.
remote: Compressing objects: 100% (11/11), done.
remote: Total 550 (delta 6), reused 15 (delta 5), pack-reused 532
Receiving objects: 100% (550/550), 6.32 MiB | 32.38 MiB/s, done.
Resolving deltas: 100% (27/27), done.
def imshow(img,text=None,should_save=False):
npimg = img.numpy()
plt.axis("off")
if text:
plt.text(75, 8, text, style='italic',fontweight='bold',
bbox={'facecolor':'white', 'alpha':0.8, 'pad':10})
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
def show_plot(iteration,loss):
plt.plot(iteration,loss)
plt.show()
class Config():
training_dir = "/content/Facial-Similarity-with-Siamese-Networks-in-Pytorch/data/faces/training"
testing_dir = "/content/Facial-Similarity-with-Siamese-Networks-in-Pytorch/data/faces/testing"
train_batch_size = 64
train_number_epochs = 100
class SiameseNetworkDataset(Dataset):
def __init__(self,imageFolderDataset,transform=None,should_invert=True):
self.imageFolderDataset = imageFolderDataset
self.transform = transform
self.should_invert = should_invert
def __getitem__(self,index):
img0_tuple = random.choice(self.imageFolderDataset.imgs)
#we need to make sure approx 50% of images are in the same class
should_get_same_class = random.randint(0,1)
if should_get_same_class:
while True:
#keep looping till the same class image is found
img1_tuple = random.choice(self.imageFolderDataset.imgs)
if img0_tuple[1]==img1_tuple[1]:
break
else:
while True:
#keep looping till a different class image is found
img1_tuple = random.choice(self.imageFolderDataset.imgs)
if img0_tuple[1] !=img1_tuple[1]:
break
img0 = Image.open(img0_tuple[0])
img1 = Image.open(img1_tuple[0])
img0 = img0.convert("L")
img1 = img1.convert("L")
if self.should_invert:
img0 = PIL.ImageOps.invert(img0)
img1 = PIL.ImageOps.invert(img1)
if self.transform is not None:
img0 = self.transform(img0)
img1 = self.transform(img1)
return img0, img1 , torch.from_numpy(np.array([int(img1_tuple[1]!=img0_tuple[1])],dtype=np.float32))
def __len__(self):
return len(self.imageFolderDataset.imgs)