Dog-Breed-120 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 dog images into specific breed categories using the SiglipForImageClassification architecture.

[!Note] Accuracy : 86.81

{'eval_loss': 0.49717578291893005,
 'eval_model_preparation_time': 0.0042,
 'eval_accuracy': 0.8681275679906085,
 'eval_runtime': 146.2493,
 'eval_samples_per_second': 69.894,
 'eval_steps_per_second': 8.739,
 'epoch': 7.0}

The model categorizes images into the following 121 classes (0-120):

Class 0: "affenpinscher"
Class 1: "afghan_hound"
Class 2: "african_hunting_dog"
Class 3: "airedale"
Class 4: "american_staffordshire_terrier"
Class 5: "appenzeller"
Class 6: "australian_terrier"
Class 7: "basenji"
Class 8: "basset"
Class 9: "beagle"
Class 10: "bedlington_terrier"
Class 11: "bernese_mountain_dog"
Class 12: "black-and-tan_coonhound"
Class 13: "blenheim_spaniel"
Class 14: "bloodhound"
Class 15: "bluetick"
Class 16: "border_collie"
Class 17: "border_terrier"
Class 18: "borzoi"
Class 19: "boston_bull"
Class 20: "bouvier_des_flandres"
Class 21: "boxer"
Class 22: "brabancon_griffon"
Class 23: "briard"
Class 24: "brittany_spaniel"
Class 25: "bull_mastiff"
Class 26: "cairn"
Class 27: "cardigan"
Class 28: "chesapeake_bay_retriever"
Class 29: "chihuahua"
Class 30: "chow"
Class 31: "clumber"
Class 32: "cocker_spaniel"
Class 33: "collie"
Class 34: "curly-coated_retriever"
Class 35: "dandie_dinmont"
Class 36: "dhole"
Class 37: "dingo"
Class 38: "doberman"
Class 39: "english_foxhound"
Class 40: "english_setter"
Class 41: "english_springer"
Class 42: "entlebucher"
Class 43: "eskimo_dog"
Class 44: "flat-coated_retriever"
Class 45: "french_bulldog"
Class 46: "german_shepherd"
Class 47: "german_short-haired_pointer"
Class 48: "giant_schnauzer"
Class 49: "golden_retriever"
Class 50: "gordon_setter"
Class 51: "great_dane"
Class 52: "great_pyrenees"
Class 53: "greater_swiss_mountain_dog"
Class 54: "groenendael"
Class 55: "ibizan_hound"
Class 56: "irish_setter"
Class 57: "irish_terrier"
Class 58: "irish_water_spaniel"
Class 59: "irish_wolfhound"
Class 60: "italian_greyhound"
Class 61: "japanese_spaniel"
Class 62: "keeshond"
Class 63: "kelpie"
Class 64: "kerry_blue_terrier"
Class 65: "komondor"
Class 66: "kuvasz"
Class 67: "labrador_retriever"
Class 68: "lakeland_terrier"
Class 69: "leonberg"
Class 70: "lhasa"
Class 71: "malamute"
Class 72: "malinois"
Class 73: "maltese_dog"
Class 74: "mexican_hairless"
Class 75: "miniature_pinscher"
Class 76: "miniature_poodle"
Class 77: "miniature_schnauzer"
Class 78: "newfoundland"
Class 79: "norfolk_terrier"
Class 80: "norwegian_elkhound"
Class 81: "norwich_terrier"
Class 82: "old_english_sheepdog"
Class 83: "otterhound"
Class 84: "papillon"
Class 85: "pekinese"
Class 86: "pembroke"
Class 87: "pomeranian"
Class 88: "pug"
Class 89: "redbone"
Class 90: "rhodesian_ridgeback"
Class 91: "rottweiler"
Class 92: "saint_bernard"
Class 93: "saluki"
Class 94: "samoyed"
Class 95: "schipperke"
Class 96: "scotch_terrier"
Class 97: "scottish_deerhound"
Class 98: "sealyham_terrier"
Class 99: "shetland_sheepdog"
Class 100: "shih-tzu"
Class 101: "siberian_husky"
Class 102: "silky_terrier"
Class 103: "soft-coated_wheaten_terrier"
Class 104: "staffordshire_bullterrier"
Class 105: "standard_poodle"
Class 106: "standard_schnauzer"
Class 107: "sussex_spaniel"
Class 108: "test"
Class 109: "tibetan_mastiff"
Class 110: "tibetan_terrier"
Class 111: "toy_poodle"
Class 112: "toy_terrier"
Class 113: "vizsla"
Class 114: "walker_hound"
Class 115: "weimaraner"
Class 116: "welsh_springer_spaniel"
Class 117: "west_highland_white_terrier"
Class 118: "whippet"
Class 119: "wire-haired_fox_terrier"
Class 120: "yorkshire_terrier"

Run with Transformers🤗

!pip install -q transformers torch pillow gradio

python

import gradio as gr
from transformers import AutoImageProcessor, SiglipForImageClassification
from PIL import Image
import torch

# Load model and processor
model_name = "prithivMLmods/Dog-Breed-120"
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)

def dog_breed_classification(image):
    """Predicts the dog breed for an image."""
    image = Image.fromarray(image).convert("RGB")
    inputs = processor(images=image, return_tensors="pt")
    
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
    
    labels = {
        "0": "affenpinscher",
        "1": "afghan_hound",
        "2": "african_hunting_dog",
        "3": "airedale",
        "4": "american_staffordshire_terrier",
        "5": "appenzeller",
        "6": "australian_terrier",
        "7": "basenji",
        "8": "basset",
        "9": "beagle",
        "10": "bedlington_terrier",
        "11": "bernese_mountain_dog",
        "12": "black-and-tan_coonhound",
        "13": "blenheim_spaniel",
        "14": "bloodhound",
        "15": "bluetick",
        "16": "border_collie",
        "17": "border_terrier",
        "18": "borzoi",
        "19": "boston_bull",
        "20": "bouvier_des_flandres",
        "21": "boxer",
        "22": "brabancon_griffon",
        "23": "briard",
        "24": "brittany_spaniel",
        "25": "bull_mastiff",
        "26": "cairn",
        "27": "cardigan",
        "28": "chesapeake_bay_retriever",
        "29": "chihuahua",
        "30": "chow",
        "31": "clumber",
        "32": "cocker_spaniel",
        "33": "collie",
        "34": "curly-coated_retriever",
        "35": "dandie_dinmont",
        "36": "dhole",
        "37": "dingo",
        "38": "doberman",
        "39": "english_foxhound",
        "40": "english_setter",
        "41": "english_springer",
        "42": "entlebucher",
        "43": "eskimo_dog",
        "44": "flat-coated_retriever",
        "45": "french_bulldog",
        "46": "german_shepherd",
        "47": "german_short-haired_pointer",
        "48": "giant_schnauzer",
        "49": "golden_retriever",
        "50": "gordon_setter",
        "51": "great_dane",
        "52": "great_pyrenees",
        "53": "greater_swiss_mountain_dog",
        "54": "groenendael",
        "55": "ibizan_hound",
        "56": "irish_setter",
        "57": "irish_terrier",
        "58": "irish_water_spaniel",
        "59": "irish_wolfhound",
        "60": "italian_greyhound",
        "61": "japanese_spaniel",
        "62": "keeshond",
        "63": "kelpie",
        "64": "kerry_blue_terrier",
        "65": "komondor",
        "66": "kuvasz",
        "67": "labrador_retriever",
        "68": "lakeland_terrier",
        "69": "leonberg",
        "70": "lhasa",
        "71": "malamute",
        "72": "malinois",
        "73": "maltese_dog",
        "74": "mexican_hairless",
        "75": "miniature_pinscher",
        "76": "miniature_poodle",
        "77": "miniature_schnauzer",
        "78": "newfoundland",
        "79": "norfolk_terrier",
        "80": "norwegian_elkhound",
        "81": "norwich_terrier",
        "82": "old_english_sheepdog",
        "83": "otterhound",
        "84": "papillon",
        "85": "pekinese",
        "86": "pembroke",
        "87": "pomeranian",
        "88": "pug",
        "89": "redbone",
        "90": "rhodesian_ridgeback",
        "91": "rottweiler",
        "92": "saint_bernard",
        "93": "saluki",
        "94": "samoyed",
        "95": "schipperke",
        "96": "scotch_terrier",
        "97": "scottish_deerhound",
        "98": "sealyham_terrier",
        "99": "shetland_sheepdog",
        "100": "shih-tzu",
        "101": "siberian_husky",
        "102": "silky_terrier",
        "103": "soft-coated_wheaten_terrier",
        "104": "staffordshire_bullterrier",
        "105": "standard_poodle",
        "106": "standard_schnauzer",
        "107": "sussex_spaniel",
        "108": "test",
        "109": "tibetan_mastiff",
        "110": "tibetan_terrier",
        "111": "toy_poodle",
        "112": "toy_terrier",
        "113": "vizsla",
        "114": "walker_hound",
        "115": "weimaraner",
        "116": "welsh_springer_spaniel",
        "117": "west_highland_white_terrier",
        "118": "whippet",
        "119": "wire-haired_fox_terrier",
        "120": "yorkshire_terrier"
    }
    
    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
    return predictions

# Create Gradio interface
iface = gr.Interface(
    fn=dog_breed_classification,
    inputs=gr.Image(type="numpy"),
    outputs=gr.Label(label="Prediction Scores"),
    title="Dog Breed Classification",
    description="Upload an image to classify it into one of the 121 dog breed categories."
)

# Launch the app
if __name__ == "__main__":
    iface.launch()

Intended Use:

The Dog-Breed-120 model is designed for dog breed image classification. It helps categorize dog images into 121 specific breed categories. Potential use cases include:

Pet Identification: Assisting pet owners and veterinarians in identifying dog breeds.
Animal Research: Supporting research in canine genetics and behavior studies.
E-commerce Applications: Enhancing pet-related product recommendations and searches.
Educational Purposes: Aiding in learning and teaching about various dog breeds.