inference.py

import json
import time
from PIL import Image
import torch
from torchvision.transforms import transforms

model = torch.load('/path/to/your/model.pth').to("cuda")
model.eval()
transform = transforms.Compose([
    transforms.Resize((448, 448)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[
        0.48145466,
        0.4578275,
        0.40821073
    ], std=[
        0.26862954,
        0.26130258,
        0.27577711
    ])
])

with open("tags_8041.json", "r") as file:
    tags = json.load(file)
allowed_tags = sorted(tags)
allowed_tags.insert(0, "placeholder0")
allowed_tags.append("placeholder1")
allowed_tags.append("explicit")
allowed_tags.append("questionable")
allowed_tags.append("safe")

image_path = "/path/to/your/image.jpg"
start = time.time()
img = Image.open(image_path).convert('RGB')
tensor = transform(img).unsqueeze(0).to("cuda")

with torch.no_grad():
    out = model(tensor)
probabilities = torch.nn.functional.sigmoid(out[0])
indices = torch.where(probabilities > 0.3)[0]
values = probabilities[indices]

for i in range(indices.size(0)):
    print(allowed_tags[indices[i]], values[i].item())

end = time.time()
print(f'Executed in {end - start} seconds')
print("\n\n", end="")