import torch, torch.nn as nn
from huggingface_hub import hf_hub_download
from torchvision.models import resnet50
from torchvision import transforms
from PIL import Image

path = hf_hub_download("ryosiswand/resnet50-stanford-cars-brand", "model.pth")
ckpt = torch.load(path, map_location="cpu", weights_only=False)

model = resnet50(weights=None)
model.fc = nn.Linear(model.fc.in_features, ckpt["num_classes"])
model.load_state_dict(ckpt["state_dict"])
model.eval()

tf = transforms.Compose([
    transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(),
    transforms.Normalize(ckpt["mean"], ckpt["std"]),
])
img = Image.open("mobil.jpg").convert("RGB")
probs = model(tf(img).unsqueeze(0)).softmax(-1)[0]
print(ckpt["class_names"][int(probs.argmax())], float(probs.max()))

Dibuat sebagai proyek Computer Vision (CNN) - Ruangguru AI Bootcamp.