Implemented Diffusers architechture from scratch!

README.md

@@ -0,0 +1,135 @@
+
+# DDPM — Fashion-MNIST
+
+A simple DDPM implementation built from scratch using PyTorch.
+
+The model learns to predict the noise added to a real Fashion-MNIST image.
+
+## Pipeline
+
+Training:
+
+    x₀ → add noise → xₜ → U-Net → predicted noise
+                              ↓
+                         MSE Loss
+
+Sampling:
+
+    Gaussian Noise
+          ↓
+        U-Net
+          ↓
+      Denoising
+          ↓
+        U-Net
+          ↓
+         ...
+          ↓
+     Generated Image
+
+## Model
+
+The U-Net takes:
+
+    (xₜ, t)
+
+and predicts:
+
+    εθ(xₜ, t)
+
+The U-Net contains:
+
+- Time embedding
+- Input convolution
+- 2 downsampling blocks
+- 2 middle ResBlocks
+- 2 upsampling blocks
+- Skip connections
+- GroupNorm
+- SiLU activation
+- Final output convolution
+
+Input:
+
+    [B, 1, 28, 28]
+
+Output:
+
+    [B, 1, 28, 28]
+
+The output represents predicted Gaussian noise.
+
+## Forward Diffusion
+
+We use:
+
+    xₜ = √ᾱₜ x₀ + √(1 - ᾱₜ) ε
+
+where:
+
+    ε ~ N(0, I)
+
+## Training
+
+For every batch:
+
+1. Take a real image x₀.
+2. Select a random timestep t.
+3. Generate Gaussian noise ε.
+4. Create xₜ using the forward diffusion process.
+5. Give xₜ and t to the U-Net.
+6. Predict the noise.
+7. Calculate MSE between predicted and actual noise.
+8. Update the U-Net.
+
+## Reverse Diffusion
+
+During generation, we start from:
+
+    xT ~ N(0, I)
+
+and move backwards:
+
+    xT → xT-1 → ... → x1 → x0
+
+At every timestep, the U-Net predicts the noise and the DDPM scheduler performs one reverse step.
+
+## Checkpoint
+
+Model weights are saved using:
+
+    .safetensors
+
+Example:
+
+    checkpoints/ddpm_fashion_mnist.safetensors
+
+The model architecture must be recreated before loading the weights.
+
+## Dataset
+
+Dataset:
+
+    Fashion-MNIST
+
+Image size:
+
+    28 × 28
+
+Channels:
+
+    1
+
+## Goal
+
+The goal of this project is to understand DDPM from first principles:
+
+    Forward Diffusion
+          ↓
+       U-Net
+          ↓
+    Noise Prediction
+          ↓
+    Reverse Diffusion
+          ↓
+    Image Generation

config.py

@@ -0,0 +1,71 @@
+
+import torch
+
+
+# =========================
+# Device
+# =========================
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+
+# =========================
+# Dataset
+# =========================
+
+IMAGE_SIZE = 28
+CHANNELS = 1
+
+
+# =========================
+# DDPM
+# =========================
+
+TIMESTEPS = 1000
+
+BETA_START = 1e-4
+BETA_END = 0.02
+
+
+# =========================
+# Model
+# =========================
+
+TIME_EMBED_DIM = 128
+
+BASE_CHANNELS = 64
+MID_CHANNELS = 128
+
+
+# =========================
+# Training
+# =========================
+
+BATCH_SIZE = 128
+EPOCHS = 20
+
+LEARNING_RATE = 2e-4
+WEIGHT_DECAY = 1e-4
+
+
+# =========================
+# Checkpoints
+# =========================
+
+CHECKPOINT_DIR = "checkpoints"
+
+MODEL_NAME = "ddpm_fashion_mnist.safetensors"
+
+
+# =========================
+# Sampling
+# =========================
+
+NUM_SAMPLES = 16
+
+
+# =========================
+# Random Seed
+# =========================
+
+SEED = 42