File size: 1,540 Bytes
e4634c2 1a260cd e4634c2 1a260cd e4634c2 3e467ea e027211 3e467ea e027211 3e467ea e4634c2 8ac071c e4634c2 1a260cd e4634c2 |
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 |
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
config_path = "TimM77/SegformerPlusPlus"
print("Starte config_load")
config = MySegformerConfig.from_pretrained(config_path)
print("Starte Model_load")
model_path = "TimM77/SegformerPlusPlus/pytorch_model.bin"
model = MySegformerForSemanticSegmentation.from_pretrained(model_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}")
|