Main commit

commit for entire Image Generation using GANs  project including structured files.

ImageGen using GANs/dcgan_main.py

@@ -0,0 +1,131 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.utils.data
+import torchvision.datasets as dset
+import torchvision.transforms as transforms
+import torchvision.utils as vutils
+
+# Setting some hyperparameters
+batchSize = 64
+imageSize = 64
+
+# Creating the transformations
+transform = transforms.Compose([
+    transforms.Resize(imageSize),
+    transforms.ToTensor(),
+    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
+])
+
+# Loading the dataset
+dataset = dset.CIFAR10(root='./data', download=True, transform=transform)
+dataloader = torch.utils.data.DataLoader(dataset, batch_size=batchSize, shuffle=True, num_workers=2)
+
+# Defining the weights_init function that takes as input a neural network m and that will initialize all its weights.
+def weights_init(m):
+    classname = m.__class__.__name__
+    if classname.find('Conv') != -1:
+        m.weight.data.normal_(0.0, 0.02)
+    elif classname.find('BatchNorm') != -1:
+        m.weight.data.normal_(1.0, 0.02)
+        m.bias.data.fill_(0)
+
+# Defining the generator
+class Generator(nn.Module):
+    def __init__(self):
+        super(Generator, self).__init__()
+        self.main = nn.Sequential(
+            nn.ConvTranspose2d(100, 512, 4, 1, 0, bias=False),
+            nn.BatchNorm2d(512),
+            nn.ReLU(True),
+            nn.ConvTranspose2d(512, 256, 4, 2, 1, bias=False),
+            nn.BatchNorm2d(256),
+            nn.ReLU(True),
+            nn.ConvTranspose2d(256, 128, 4, 2, 1, bias=False),
+            nn.BatchNorm2d(128),
+            nn.ReLU(True),
+            nn.ConvTranspose2d(128, 64, 4, 2, 1, bias=False),
+            nn.BatchNorm2d(64),
+            nn.ReLU(True),
+            nn.ConvTranspose2d(64, 3, 4, 2, 1, bias=False),
+            nn.Tanh()
+        )
+
+    def forward(self, input):
+        return self.main(input)
+
+# Creating the generator
+netG = Generator()
+netG.apply(weights_init)
+
+# Defining the discriminator
+class Discriminator(nn.Module):
+    def __init__(self):
+        super(Discriminator, self).__init__()
+        self.main = nn.Sequential(
+            nn.Conv2d(3, 64, 4, 2, 1, bias=False),
+            nn.LeakyReLU(0.2, inplace=True),
+            nn.Conv2d(64, 128, 4, 2, 1, bias=False),
+            nn.BatchNorm2d(128),
+            nn.LeakyReLU(0.2, inplace=True),
+            nn.Conv2d(128, 256, 4, 2, 1, bias=False),
+            nn.BatchNorm2d(256),
+            nn.LeakyReLU(0.2, inplace=True),
+            nn.Conv2d(256, 512, 4, 2, 1, bias=False),
+            nn.BatchNorm2d(512),
+            nn.LeakyReLU(0.2, inplace=True),
+            nn.Conv2d(512, 1, 4, 1, 0, bias=False),
+            nn.Sigmoid()
+        )
+
+    def forward(self, input):
+        return self.main(input).view(-1)
+
+# Creating the discriminator
+netD = Discriminator()
+netD.apply(weights_init)
+
+# Training the DCGANs
+criterion = nn.BCELoss()
+optimizerD = optim.Adam(netD.parameters(), lr=0.0002, betas=(0.5, 0.999))
+optimizerG = optim.Adam(netG.parameters(), lr=0.0002, betas=(0.5, 0.999))
+
+for epoch in range(25):
+    for i, data in enumerate(dataloader, 0):
+
+        # 1st Step: Updating the weights of the neural network of the discriminator
+        netD.zero_grad()
+
+        # Training the discriminator with a real image of the dataset
+        real, _ = data
+        input = real
+        target = torch.ones(input.size(0))
+        output = netD(input)
+        errD_real = criterion(output, target)
+
+        # Training the discriminator with a fake image generated by the generator
+        noise = torch.randn(input.size(0), 100, 1, 1)
+        fake = netG(noise)
+        target = torch.zeros(input.size(0))
+        output = netD(fake.detach())
+        errD_fake = criterion(output, target)
+
+        # Backpropagating the total error
+        errD = errD_real + errD_fake
+        errD.backward()
+        optimizerD.step()
+
+        # 2nd Step: Updating the weights of the neural network of the generator
+        netG.zero_grad()
+        target = torch.ones(input.size(0))
+        output = netD(fake)
+        errG = criterion(output, target)
+        errG.backward()
+        optimizerG.step()
+
+        # 3rd Step: Printing the losses and saving the real images and the generated images of the minibatch every 100 steps
+        print('[%d/%d][%d/%d] Loss_D: %.4f Loss_G: %.4f' % (epoch, 25, i, len(dataloader), errD.item(), errG.item()))
+        if i % 100 == 0:
+            vutils.save_image(real, '%s/real_samples.png' % "./results", normalize=True)
+            fake = netG(noise)
+            vutils.save_image(fake.data, '%s/fake_samples_epoch_%03d.png' % ("./results", epoch), normalize=True)

ImageGen using GANs/readme.txt

@@ -0,0 +1,36 @@
+# DCGAN: Deep Convolutional Generative Adversarial Network
+
+Welcome to the Image generation using GANs, a deep convolutional generative adversarial network implemented in PyTorch! This project is designed to generate realistic images from random noise using the power of deep learning.
+
+![DCGAN Image](https://github.com/chiragHimself/dcgan_random/raw/main/results/fake_samples_epoch_024.png)
+
+## Overview
+- **Project Name**: ImageGen using GANs
+- **Description**: A deep convolutional generative adversarial network to generate realistic images.
+- **Framework**: PyTorch 2.2.1
+- **Training Device**: RTX 3050 Ti with CUDA 11.2
+- **IDE**: Spyder (can be run on other IDEs and Google Colab)
+
+## Dependencies
+- `torch`
+- `torch.nn`
+- `torch.optim`
+- `torch.utils.data`
+- `torchvision.datasets`
+- `torchvision.transforms`
+- `torchvision.utils`
+
+## Training Data
+The training data for this project is obtained from the CIFAR-10 open dataset. It is downloaded to a local directory named `data`, where the training is conducted.
+
+## Training Details
+- **Epochs**: 25
+- **Training Time**: Approximately 4 hours
+- **Result**: various batch png's are included in the repository, showcasing the generated images after each epoch. Please note that this file will be overwritten if you run the code in your IDE.
+
+## Generated Images
+Here are some samples of the generated images produced by the DCGAN model:
+
+![Generated Image 1](https://github.com/chiragHimself/dcgan_random/blob/main/results/fake_samples_epoch_000.png)
+![Generated Image 2](https://github.com/chiragHimself/dcgan_random/blob/main/results/fake_samples_epoch_006.png)
+![Generated Image 3](https://github.com/chiragHimself/dcgan_random/blob/main/results/fake_samples_epoch_024.png)