config.py

import albumentations as A
import cv2
import torch

from albumentations.pytorch import ToTensorV2


DEVICE = "cuda" if torch.cuda.is_available() else "cpu"


IMAGE_SIZE = 416
transforms = A.Compose(
    [
        A.LongestMaxSize(max_size=IMAGE_SIZE),
        A.PadIfNeeded(
            min_height=IMAGE_SIZE, min_width=IMAGE_SIZE, border_mode=cv2.BORDER_CONSTANT
        ),
        A.Normalize(mean=[0, 0, 0], std=[1, 1, 1], max_pixel_value=255,),
        ToTensorV2(),
    ],
)


ANCHORS = [
    [(0.28, 0.22), (0.38, 0.48), (0.9, 0.78)],
    [(0.07, 0.15), (0.15, 0.11), (0.14, 0.29)],
    [(0.02, 0.03), (0.04, 0.07), (0.08, 0.06)],
]  # Note these have been rescaled to be between [0, 1]

S = [IMAGE_SIZE // 32, IMAGE_SIZE // 16, IMAGE_SIZE // 8]

scaled_anchors = (
    torch.tensor(ANCHORS)
    * torch.tensor(S).unsqueeze(1).unsqueeze(1).repeat(1, 3, 2)
).to(DEVICE)

PASCAL_CLASSES = [
    "aeroplane",
    "bicycle",
    "bird",
    "boat",
    "bottle",
    "bus",
    "car",
    "cat",
    "chair",
    "cow",
    "diningtable",
    "dog",
    "horse",
    "motorbike",
    "person",
    "pottedplant",
    "sheep",
    "sofa",
    "train",
    "tvmonitor"
]