File size: 2,443 Bytes
d3b096b 274807d d3b096b 274807d d3b096b 274807d d3b096b 274807d d3b096b 274807d d3b096b 274807d d3b096b 274807d d3b096b 274807d d3b096b 274807d d3b096b 274807d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | """Imager-1-Tiny - Model architecture and inference."""
import os
import torch
import torch.nn as nn
from torchvision import models
from PIL import Image
from .preprocess import get_transform
class ImagerTiny(nn.Module):
"""ResNet-50 backbone with a single-logit binary head."""
def __init__(self, pretrained: bool = False):
super().__init__()
self.backbone = models.resnet50(
weights="IMAGENET1K_V1" if pretrained else None
)
in_features = self.backbone.fc.in_features
self.backbone.fc = nn.Linear(in_features, 1)
def forward(self, x):
return self.backbone(x)
def load_model(weights_path: str = None, device: str = "cpu") -> ImagerTiny:
"""Load the trained Imager-1-Tiny model."""
if weights_path is None:
weights_path = os.path.join(
os.path.dirname(__file__), "..", "model", "model_imager-1-tiny.pth"
)
model = ImagerTiny(pretrained=False)
state = torch.load(weights_path, map_location=device)
model.load_state_dict(state)
model.to(device)
model.eval()
return model
def predict(image, model: ImagerTiny = None, device: str = "cpu") -> dict:
"""
Predict whether an image is Real or AI-Generated.
Args:
image: PIL.Image, str path, or file-like object.
model: Pre-loaded ImagerTiny (optional).
device: "cpu" or "cuda".
Returns:
dict with probability, label, confidence.
"""
if model is None:
model = load_model(device=device)
transform = get_transform(train=False)
if isinstance(image, str):
image = Image.open(image)
elif hasattr(image, "read"):
image = Image.open(image)
image = image.convert("RGB")
tensor = transform(image).unsqueeze(0).to(device)
with torch.no_grad():
prob = torch.sigmoid(model(tensor)).item()
label = "AI-Generated" if prob > MODEL_CONFIG["threshold"] else "Real"
return {
"probability": round(prob, 4),
"label": label,
"confidence": round(prob if label == "AI-Generated" else 1 - prob, 4),
}
MODEL_CONFIG = {
"name": "imager-1-tiny",
"architecture": "resnet50",
"num_params": 25_000_000,
"input_size": 224,
"num_classes": 1,
"threshold": 0.385,
"labels": {0: "Real", 1: "AI-Generated"},
"normalize": {
"mean": [0.485, 0.456, 0.406],
"std": [0.229, 0.224, 0.225],
},
}
|