Update README.md

README.md

@@ -3,6 +3,9 @@ license: apache-2.0
 datasets:
 - Bruece/domainnet-126-by-class-painting
 ---
+# **Painting-126-DomainNet**
+
+> **Painting-126-DomainNet** is an image classification vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for a single-label classification task. It is designed to classify paintings into 126 domain categories using the **SiglipForImageClassification** architecture.
 
 ```py
 Classification Report:
@@ -138,4 +141,223 @@ the_Great_Wall_of_China     0.8244    0.8710    0.8471       124
                accuracy                         0.8533     24032
               macro avg     0.7686    0.7273    0.7299     24032
            weighted avg     0.8445    0.8533    0.8424     24032
-```
+```
+
+
+The model categorizes images into the following 126 classes:
+- **Class 0:** "aircraft_carrier"
+- **Class 1:** "alarm_clock"
+- **Class 2:** "ant"
+- **Class 3:** "anvil"
+- **Class 4:** "asparagus"
+- **Class 5:** "axe"
+- **Class 6:** "banana"
+- **Class 7:** "basket"
+- **Class 8:** "bathtub"
+- **Class 9:** "bear"
+- **Class 10:** "bee"
+- **Class 11:** "bird"
+- **Class 12:** "blackberry"
+- **Class 13:** "blueberry"
+- **Class 14:** "bottlecap"
+- **Class 15:** "broccoli"
+- **Class 16:** "bus"
+- **Class 17:** "butterfly"
+- **Class 18:** "cactus"
+- **Class 19:** "cake"
+- **Class 20:** "calculator"
+- **Class 21:** "camel"
+- **Class 22:** "camera"
+- **Class 23:** "candle"
+- **Class 24:** "cannon"
+- **Class 25:** "canoe"
+- **Class 26:** "carrot"
+- **Class 27:** "castle"
+- **Class 28:** "cat"
+- **Class 29:** "ceiling_fan"
+- **Class 30:** "cell_phone"
+- **Class 31:** "cello"
+- **Class 32:** "chair"
+- **Class 33:** "chandelier"
+- **Class 34:** "coffee_cup"
+- **Class 35:** "compass"
+- **Class 36:** "computer"
+- **Class 37:** "cow"
+- **Class 38:** "crab"
+- **Class 39:** "crocodile"
+- **Class 40:** "cruise_ship"
+- **Class 41:** "dog"
+- **Class 42:** "dolphin"
+- **Class 43:** "dragon"
+- **Class 44:** "drums"
+- **Class 45:** "duck"
+- **Class 46:** "dumbbell"
+- **Class 47:** "elephant"
+- **Class 48:** "eyeglasses"
+- **Class 49:** "feather"
+- **Class 50:** "fence"
+- **Class 51:** "fish"
+- **Class 52:** "flamingo"
+- **Class 53:** "flower"
+- **Class 54:** "foot"
+- **Class 55:** "fork"
+- **Class 56:** "frog"
+- **Class 57:** "giraffe"
+- **Class 58:** "goatee"
+- **Class 59:** "grapes"
+- **Class 60:** "guitar"
+- **Class 61:** "hammer"
+- **Class 62:** "helicopter"
+- **Class 63:** "helmet"
+- **Class 64:** "horse"
+- **Class 65:** "kangaroo"
+- **Class 66:** "lantern"
+- **Class 67:** "laptop"
+- **Class 68:** "leaf"
+- **Class 69:** "lion"
+- **Class 70:** "lipstick"
+- **Class 71:** "lobster"
+- **Class 72:** "microphone"
+- **Class 73:** "monkey"
+- **Class 74:** "mosquito"
+- **Class 75:** "mouse"
+- **Class 76:** "mug"
+- **Class 77:** "mushroom"
+- **Class 78:** "onion"
+- **Class 79:** "panda"
+- **Class 80:** "peanut"
+- **Class 81:** "pear"
+- **Class 82:** "peas"
+- **Class 83:** "pencil"
+- **Class 84:** "penguin"
+- **Class 85:** "pig"
+- **Class 86:** "pillow"
+- **Class 87:** "pineapple"
+- **Class 88:** "potato"
+- **Class 89:** "power_outlet"
+- **Class 90:** "purse"
+- **Class 91:** "rabbit"
+- **Class 92:** "raccoon"
+- **Class 93:** "rhinoceros"
+- **Class 94:** "rifle"
+- **Class 95:** "saxophone"
+- **Class 96:** "screwdriver"
+- **Class 97:** "sea_turtle"
+- **Class 98:** "see_saw"
+- **Class 99:** "sheep"
+- **Class 100:** "shoe"
+- **Class 101:** "skateboard"
+- **Class 102:** "snake"
+- **Class 103:** "speedboat"
+- **Class 104:** "spider"
+- **Class 105:** "squirrel"
+- **Class 106:** "strawberry"
+- **Class 107:** "streetlight"
+- **Class 108:** "string_bean"
+- **Class 109:** "submarine"
+- **Class 110:** "swan"
+- **Class 111:** "table"
+- **Class 112:** "teapot"
+- **Class 113:** "teddy-bear"
+- **Class 114:** "television"
+- **Class 115:** "the_Eiffel_Tower"
+- **Class 116:** "the_Great_Wall_of_China"
+- **Class 117:** "tiger"
+- **Class 118:** "toe"
+- **Class 119:** "train"
+- **Class 120:** "truck"
+- **Class 121:** "umbrella"
+- **Class 122:** "vase"
+- **Class 123:** "watermelon"
+- **Class 124:** "whale"
+- **Class 125:** "zebra"
+
+# **Run with Transformers🤗**
+
+```python
+!pip install -q transformers torch pillow gradio
+```
+
+```python
+import gradio as gr
+from transformers import AutoImageProcessor, SiglipForImageClassification
+from transformers.image_utils import load_image
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/Painting-126-DomainNet"
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+
+def painting_classification(image):
+    """Predicts the painting category for an input image."""
+    # Convert the input numpy array to a PIL image and ensure it is in RGB format
+    image = Image.fromarray(image).convert("RGB")
+    
+    # Process the image for the model
+    inputs = processor(images=image, return_tensors="pt")
+    
+    # Get predictions from the model without gradient computation
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        # Convert logits to probabilities using softmax
+        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
+    
+    # Define the label mapping for each class index
+    labels = {
+        "0": "aircraft_carrier", "1": "alarm_clock", "2": "ant", "3": "anvil", "4": "asparagus",
+        "5": "axe", "6": "banana", "7": "basket", "8": "bathtub", "9": "bear",
+        "10": "bee", "11": "bird", "12": "blackberry", "13": "blueberry", "14": "bottlecap",
+        "15": "broccoli", "16": "bus", "17": "butterfly", "18": "cactus", "19": "cake",
+        "20": "calculator", "21": "camel", "22": "camera", "23": "candle", "24": "cannon",
+        "25": "canoe", "26": "carrot", "27": "castle", "28": "cat", "29": "ceiling_fan",
+        "30": "cell_phone", "31": "cello", "32": "chair", "33": "chandelier", "34": "coffee_cup",
+        "35": "compass", "36": "computer", "37": "cow", "38": "crab", "39": "crocodile",
+        "40": "cruise_ship", "41": "dog", "42": "dolphin", "43": "dragon", "44": "drums",
+        "45": "duck", "46": "dumbbell", "47": "elephant", "48": "eyeglasses", "49": "feather",
+        "50": "fence", "51": "fish", "52": "flamingo", "53": "flower", "54": "foot",
+        "55": "fork", "56": "frog", "57": "giraffe", "58": "goatee", "59": "grapes",
+        "60": "guitar", "61": "hammer", "62": "helicopter", "63": "helmet", "64": "horse",
+        "65": "kangaroo", "66": "lantern", "67": "laptop", "68": "leaf", "69": "lion",
+        "70": "lipstick", "71": "lobster", "72": "microphone", "73": "monkey", "74": "mosquito",
+        "75": "mouse", "76": "mug", "77": "mushroom", "78": "onion", "79": "panda",
+        "80": "peanut", "81": "pear", "82": "peas", "83": "pencil", "84": "penguin",
+        "85": "pig", "86": "pillow", "87": "pineapple", "88": "potato", "89": "power_outlet",
+        "90": "purse", "91": "rabbit", "92": "raccoon", "93": "rhinoceros", "94": "rifle",
+        "95": "saxophone", "96": "screwdriver", "97": "sea_turtle", "98": "see_saw", "99": "sheep",
+        "100": "shoe", "101": "skateboard", "102": "snake", "103": "speedboat", "104": "spider",
+        "105": "squirrel", "106": "strawberry", "107": "streetlight", "108": "string_bean",
+        "109": "submarine", "110": "swan", "111": "table", "112": "teapot", "113": "teddy-bear",
+        "114": "television", "115": "the_Eiffel_Tower", "116": "the_Great_Wall_of_China",
+        "117": "tiger", "118": "toe", "119": "train", "120": "truck", "121": "umbrella",
+        "122": "vase", "123": "watermelon", "124": "whale", "125": "zebra"
+    }
+    
+    # Map each label to its corresponding probability (rounded)
+    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
+    return predictions
+
+# Create Gradio interface for the painting classifier
+iface = gr.Interface(
+    fn=painting_classification,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(label="Prediction Scores"),
+    title="Painting-126-DomainNet Classification",
+    description="Upload a painting to classify it into one of 126 categories."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()
+```
+
+# **Intended Use:**
+
+The **Painting-126-DomainNet** model is designed for painting image classification. It categorizes paintings into a wide range of domains—from objects like an "aircraft_carrier" or "alarm_clock" to animals, plants, and everyday items. Potential use cases include:
+
+- **Art Curation & Analysis:** Assisting galleries and museums in organizing and categorizing artworks.
+- **Creative Search Engines:** Enabling painting-based search for art inspiration and research.
+- **Educational Tools:** Supporting art education by categorizing and retrieving visual resources.
+- **Computer Vision Research:** Providing a benchmark dataset for studies in painting recognition and domain adaptation tasks.