Upload 2 files

diffuser/run.py

@@ -0,0 +1,30 @@
+from utils import create_stable_diffusion_model, run_diffuser
+import opensr_test
+import matplotlib.pyplot as plt
+
+# Load the model
+model = create_stable_diffusion_model(device="cuda")
+
+# Load the dataset
+dataset = opensr_test.load("naip")
+lr_dataset, hr_dataset = dataset["L2A"], dataset["HRharm"]
+
+# Run the model
+results = run_diffuser(
+    model=model,
+    lr=lr_dataset[5][:,0:64, 0:64],
+    hr=hr_dataset[5][:,0:256, 0:256],
+    device="cuda"
+)
+
+# Display the results
+fig, ax = plt.subplots(1, 3, figsize=(10, 5))
+ax[0].imshow(results["lr"].transpose(1, 2, 0)/3000)
+ax[0].set_title("LR")
+ax[0].axis("off")
+ax[1].imshow(results["sr"].transpose(1, 2, 0)/3000)
+ax[1].set_title("SR")
+ax[1].axis("off")
+ax[2].imshow(results["hr"].transpose(1, 2, 0) / 3000)
+ax[2].set_title("HR")
+plt.show()

diffuser/utils.py

@@ -0,0 +1,81 @@
+from diffusers import LDMSuperResolutionPipeline
+import numpy as np
+import opensr_test
+import torch
+import pickle
+from typing import Union
+
+
+def create_stable_diffusion_model(
+    device: Union[str, torch.device] = "cuda"
+) -> LDMSuperResolutionPipeline:
+    """ Create the stable diffusion model
+
+    Returns:
+        LDMSuperResolutionPipeline: The model to use for
+            super resolution.
+    """
+    model_id = "CompVis/ldm-super-resolution-4x-openimages"
+    pipeline = LDMSuperResolutionPipeline.from_pretrained(model_id)
+    pipeline = pipeline.to(device)
+    return pipeline
+
+def run_diffuser(
+    model: LDMSuperResolutionPipeline,
+    lr: torch.Tensor,
+    hr: torch.Tensor,
+    device: Union[str, torch.device] = "cuda"    
+) -> dict:
+    """ Run the model on the low resolution image
+
+    Args:
+        model (LDMSuperResolutionPipeline): The model to use
+        lr (torch.Tensor): The low resolution image
+        hr (torch.Tensor): The high resolution image
+        device (Union[str, torch.device], optional): The device
+            to use. Defaults to "cuda".
+
+    Returns:
+        dict: The results of the model
+    """
+
+    # move the images to the device
+    lr = (torch.from_numpy(lr[[3, 2, 1]]) / 2000).to(device).clamp(0, 1)
+    
+    if lr.shape[1] == 121:
+        # add padding
+        lr = torch.nn.functional.pad(
+            lr[None],
+            pad=(3, 4, 3, 4),
+            mode='reflect'
+        ).squeeze()
+    
+        # run the model
+        with torch.no_grad():
+            sr = model(lr[None], num_inference_steps=100, eta=1)
+            sr = torch.from_numpy(
+                np.array(sr.images[0])/255
+            ).permute(2,0,1).float()
+
+        # remove padding
+        sr = sr[:, 3*4:-4*4, 3*4:-4*4]
+        lr = lr[:, 3:-4, 3:-4]
+    else:
+        # run the model
+        with torch.no_grad():
+            sr = model(lr[None], num_inference_steps=100, eta=1)
+            sr = torch.from_numpy(
+                np.array(sr.images[0])/255
+            ).permute(2,0,1).float()
+
+    lr = (lr.cpu().numpy() * 2000).astype(np.uint16)
+    hr = ((hr[0:3] / 2000).clip(0, 1) * 2000).astype(np.uint16)
+    sr = (sr.cpu().numpy() * 2000).astype(np.uint16)
+
+    results = {
+        "lr": lr,
+        "hr": hr,
+        "sr": sr
+    }
+    
+    return results