Create code.txt

code.txt

@@ -0,0 +1,75 @@
+!pip install -U adapter-transformers
+!pip install -U transformers
+!pip install torch torchvision torchaudio
+!pip install opencv-python
+import gradio as gr
+from transformers import CLIPProcessor, CLIPModel
+from PIL import Image
+import torch
+import cv2
+
+# Load the CLIP model and processor
+model = CLIPModel.from_pretrained("Taarhoinc/TaarhoGen1")
+processor = CLIPProcessor.from_pretrained("Taarhoinc/TaarhoGen1")
+
+# Load the object detection model (YOLOv5 example)
+model_path = 'yolov5s.pt'  # Replace with the path to your YOLOv5 model
+object_detection_model = torch.hub.load('ultralytics/yolov5', 'custom', path=model_path)
+
+# Define the function to describe a floor plan with sizes
+def describe_floorplan_with_sizes(floorplan_image: Image.Image, top_k: int = 3):
+    """Describes a floor plan drawing by listing components and their sizes."""
+
+    # Define a list of common floor plan components
+    components = [
+        "bedroom",
+        "kitchen",
+        "bathroom",
+        "living room",
+        "dining room",
+        "hallway",
+        "garage",
+        "balcony",
+        "stairs",
+        "door",
+        "window",
+    ]
+
+    # Perform object detection
+    results = object_detection_model(floorplan_image)
+
+    # Get detected objects and bounding boxes
+    detections = results.pandas().xyxy[0]
+
+    # Filter detections based on confidence and class names
+    threshold = 0.5  # Adjust as needed
+    filtered_detections = detections[
+        (detections['confidence'] > threshold)
+        & (detections['name'].isin(components))
+    ]
+
+    # Estimate sizes (assuming a scale of 1 pixel = 0.1 feet)
+    scale = 0.1  # Adjust according to the actual scale of the floor plan
+    component_sizes = []
+    for index, row in filtered_detections.iterrows():
+        width = (row['xmax'] - row['xmin']) * scale
+        height = (row['ymax'] - row['ymin']) * scale
+        component_sizes.append(f"{row['name']}: {width:.2f}ft x {height:.2f}ft")
+
+    # Combine with CLIP-based description
+    clip_description = describe_floorplan(floorplan_image, top_k)
+    final_description = clip_description + ", " + ", ".join(component_sizes)
+
+    return final_description
+
+# Create the Gradio interface
+gr.Interface(
+    fn=describe_floorplan_with_sizes,
+    inputs=[
+        gr.Image(label="Upload a floor plan drawing", type="pil"),
+        gr.Slider(1, 10, step=1, value=3, label="Number of components to detect"),
+    ],
+    outputs=gr.Label(label="Detected Components with Sizes"),
+    title="Floor Plan Description with TaarhoGen1 and Sizes",
+    description="Upload a floor plan drawing to get a list of detected components and their sizes.",
+).launch()