preTrainedTest.py

import torch
from PIL import Image
import torchvision.transforms as T
import numpy as np
import os

from modeling_my_segformer import MySegformerForSemanticSegmentation
from mix_vision_transformer_config import MySegformerConfig

# Gerät auswählen
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Using device: {device}")

# Modell laden
model_name_or_path = "TimM77/SegformerPlusPlus"
print("Starte config_load")
config = MySegformerConfig.from_pretrained(model_name_or_path)
print("Starte Model_load")
model = MySegformerForSemanticSegmentation.from_pretrained(model_name_or_path, config=config)
model.to(device).eval()

# Bild laden
image_path = "segformer_plusplus/cityscape/berlin_000543_000019_leftImg8bit.png"
image = Image.open(image_path).convert("RGB")

# Preprocessing
transform = T.Compose([
    T.Resize((512, 512)),
    T.ToTensor(),
    T.Normalize(mean=[0.485, 0.456, 0.406],
                std=[0.229, 0.224, 0.225])
])
input_tensor = transform(image).unsqueeze(0).to(device)

print("Modell geladen, Bild geladen, Preprocessing abgeschlossen")

# Inferenz
with torch.no_grad():
    output = model(input_tensor)
    logits = output.logits if hasattr(output, "logits") else output
    pred = torch.argmax(logits, dim=1).squeeze(0).cpu().numpy()

# Ergebnis als Textdatei speichern
output_path = os.path.join("segformer_plusplus", "cityscapes_prediction_output_overHF.txt")
np.savetxt(output_path, pred, fmt="%d")
print(f"Prediction saved as {output_path}")