test commit

app.py

@@ -1,154 +1,137 @@
 import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+import torch.nn as nn
+import torchvision.transforms as transforms
+from PIL import Image
+import numpy as np
+import os
+
+# Check if CUDA is available
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+print(f"Using device: {device}")
+
+class DeblurNet(nn.Module):
+    def __init__(self):
+        super(DeblurNet, self).__init__()
+        
+        # Encoder
+        self.enc_conv1 = self.conv_block(3, 64)
+        self.enc_conv2 = self.conv_block(64, 128)
+        self.enc_conv3 = self.conv_block(128, 256)
+        
+        # Bottleneck
+        self.bottleneck = self.conv_block(256, 512)
+        
+        # Decoder with residual connections
+        self.dec_conv1 = self.conv_block(512 + 256, 256)
+        self.dec_conv2 = self.conv_block(256 + 128, 128)
+        self.dec_conv3 = self.conv_block(128 + 64, 64)
+        self.final_conv = nn.Conv2d(64, 3, kernel_size=3, padding=1)
+        
+        # Pooling and upsampling
+        self.pool = nn.MaxPool2d(2, 2)
+        self.upsample = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
+    
+    def conv_block(self, in_channels, out_channels):
+        return nn.Sequential(
+            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True)
+        )
+    
+    def forward(self, x):
+        # Encoder
+        x1 = self.enc_conv1(x)
+        x2 = self.pool(x1)
+        
+        x2 = self.enc_conv2(x2)
+        x3 = self.pool(x2)
+        
+        x3 = self.enc_conv3(x3)
+        x4 = self.pool(x3)
+        
+        # Bottleneck
+        x4 = self.bottleneck(x4)
+        
+        # Decoder with skip connections
+        x = self.upsample(x4)
+        x = torch.cat([x, x3], dim=1)
+        x = self.dec_conv1(x)
+        
+        x = self.upsample(x)
+        x = torch.cat([x, x2], dim=1)
+        x = self.dec_conv2(x)
+        
+        x = self.upsample(x)
+        x = torch.cat([x, x1], dim=1)
+        x = self.dec_conv3(x)
+        
+        x = self.final_conv(x)
+        return torch.tanh(x)
+
+# Load model
+model = DeblurNet().to(device)
+model_path = os.path.join('model', 'best_deblur_model.pth')
+model.load_state_dict(torch.load(model_path, map_location=device))
+model.eval()
+
+# Image processing functions
+transform = transforms.Compose([
+    transforms.Resize((256, 256)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+])
+
+def postprocess_image(tensor):
+    tensor = tensor * 0.5 + 0.5
+    tensor = torch.clamp(tensor, 0, 1)
+    image = tensor.cpu().detach().numpy()
+    image = np.transpose(image, (1, 2, 0))
+    return (image * 255).astype(np.uint8)
+
+def deblur_image(input_image):
+    if input_image is None:
+        return None
+    
+    try:
+        # Convert to PIL Image
+        if isinstance(input_image, np.ndarray):
+            input_image = Image.fromarray(input_image)
+        
+        # Save original size
+        original_size = input_image.size
+        
+        # Preprocess
+        input_tensor = transform(input_image).unsqueeze(0).to(device)
+        
+        # Inference
+        with torch.no_grad():
+            output_tensor = model(input_tensor)
+        
+        # Postprocess
+        output_image = postprocess_image(output_tensor[0])
+        
+        # Resize back to original size
+        output_image = Image.fromarray(output_image).resize(original_size)
+        return np.array(output_image)
+    
+    except Exception as e:
+        print(f"Error processing image: {e}")
+        return None
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=deblur_image,
+    inputs=gr.Image(type="numpy", label="Upload Blurry Image"),
+    outputs=gr.Image(type="numpy", label="Deblurred Result"),
+    title="Image Deblurring",
+    description="Upload a blurry image and get it deblurred using deep learning.",
+    examples=[
+        ["examples/example1.jpg"],
+        ["examples/example2.jpg"]
+    ]
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

model/best_deblur_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652ed502848fee131c3812b46cf5e72dc7a8c1d37f74c21b2a90eee031ac4d21
+size 31149520