Update README.md

README.md

@@ -4,4 +4,76 @@ datasets:
 base_model:
 - microsoft/resnet-18
 pipeline_tag: image-classification
----
+---
+# AutoInspect — Car View Classifier (ResNet18)
+
+Модель для определения ракурса автомобиля на изображении.
+Часть проекта **AutoInspect** (pipeline: *view classification → car parts segmentation → damage segmentation*).
+
+## Task
+
+Multi-class классификация ракурса автомобиля (9 классов).
+
+## Labels
+
+```python
+CLASS_NAMES = [
+"back",
+"back-left",
+"back-right",
+"front",
+"front-left",
+"front-right",
+"left",
+"other",
+"right",
+]
+```
+
+## How to use
+
+### Load model
+
+```python
+import torch
+import torch.nn as nn
+from torchvision import models, transforms
+from PIL import Image
+
+CLASS_NAMES = [
+"back", "back-left", "back-right",
+"front", "front-left", "front-right",
+"left", "other", "right"
+]
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model = models.resnet18(weights=None)
+model.fc = nn.Linear(model.fc.in_features, len(CLASS_NAMES))
+
+state_dict = torch.load("best_car_view_model.pth", map_location=device)
+model.load_state_dict(state_dict)
+
+model.eval()
+model.to(device)
+```
+
+### Predict
+
+```python
+preprocess = transforms.Compose([
+transforms.Resize((224, 224)),
+transforms.ToTensor(),
+transforms.Normalize([0.485, 0.456, 0.406],
+[0.229, 0.224, 0.225])
+])
+
+img = Image.open("car.jpg").convert("RGB")
+x = preprocess(img).unsqueeze(0).to(device)
+
+with torch.no_grad():
+logits = model(x)
+pred = torch.argmax(logits, dim=1).item()
+
+print("Prediction:", CLASS_NAMES[pred])
+```