Upload README.md with huggingface_hub

README.md

@@ -19,7 +19,7 @@ This model is a diffusion-based model for unconditional image generation of **la
 - **Resolution:** Latent resolution of 32x32 to generate 256x256 final images
 - **Dataset:** Lesion2D VH split (FLAIR MRI slices) (70% of the dataset)
 - **Channels:** 4 (latents are multi-channel representations of the original images)
-- **Epochs:** 50
+- **Epochs:** 100
 - **Batch size:** 16
 - **Optimizer:** AdamW with:
   - Learning Rate: `1.0e-4`
@@ -35,7 +35,7 @@ This model is a diffusion-based model for unconditional image generation of **la
   - `beta_start`: 0.0001
   - `beta_end`: 0.02
 - **Hardware:** Trained on **NVIDIA GPUs** with a distributed dataloader using 12 workers.
-- **Memory Consumption:** Approx. **11 GB** during training.
+- **Memory Consumption:** Approx. **2.5 GB** during training.
 
 ## U-Net Architecture
 - **Down Blocks:** [DownBlock2D, DownBlock2D, DownBlock2D, DownBlock2D, AttnDownBlock2D, DownBlock2D]