cv-research

[project]
name = "cv-research"
version = "0.1.0"
description = "Computer vision research environment"
requires-python = "==3.12.*"
dependencies = [
  "torch==2.10.0",
  "torchvision==0.25.0",
  "torchaudio==2.10.0",
  "ultralytics==8.4.14",
  "timm==1.0.24",
  "albumentations==2.0.8",
  "segmentation-models-pytorch==0.5.0",
  "supervision==0.27.0.post1",
  "opencv-python==4.13.0.92",
  "ipykernel==7.2.0",
  "pytest==9.0.2",
  "ruff==0.15.2",
]

[tool.uv]
package = false

uv run python -c "import torch, ultralytics, timm, albumentations, cv2; print('torch', torch.__version__); print('ultralytics', ultralytics.__version__); print('opencv', cv2.__version__)"

import timm
import torch
from torchvision import transforms
from PIL import Image

model = timm.create_model("efficientnet_b0", pretrained=True, num_classes=10)
model.eval()

transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])

img = transform(Image.open("sample.jpg")).unsqueeze(0)
with torch.no_grad():
    output = model(img)
    pred = output.argmax(dim=1).item()
    print(f"Predicted class: {pred}")

from ultralytics import YOLO

# 사전학습 모델로 추론
model = YOLO("yolo11n.pt")
results = model("image.jpg")
results[0].show()

# 커스텀 데이터셋으로 학습
model = YOLO("yolo11n.pt")
model.train(data="dataset.yaml", epochs=50, imgsz=640, batch=16)

import albumentations as A
from albumentations.pytorch import ToTensorV2

transform = A.Compose([
    A.RandomResizedCrop(height=224, width=224, scale=(0.8, 1.0)),
    A.HorizontalFlip(p=0.5),
    A.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.1),
    A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
    ToTensorV2(),
], bbox_params=A.BboxParams(format="pascal_voc", label_fields=["labels"]))  # Detection용