format

Signed-off-by: Can-Zhao <[email protected]>

generation/maisi/README.md

@@ -50,7 +50,6 @@ We retrained several state-of-the-art diffusion model-based methods using our da
 | 512x512x768   | [80,80,112], 8 patches                 | 4                           | 55G         | 904s    | 48s      |
 
 
-
 The experiment was tested on A100 80G GPU. 
 
 During inference, the peak GPU memory usage happens during the autoencoder decoding latent features.

generation/maisi/scripts/inference.py

@@ -231,5 +231,5 @@ def main():
     )
     torch.cuda.reset_peak_memory_stats()
     main()
-    peak_memory_gb = torch.cuda.max_memory_allocated() / (1024 ** 3)  # Convert to GB
+    peak_memory_gb = torch.cuda.max_memory_allocated() / (1024**3)  # Convert to GB
     print(f"Peak GPU memory usage: {peak_memory_gb:.2f} GB")