319 lines
11 KiB
Plaintext
319 lines
11 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# 01 — Příprava datasetu VisDrone\n",
|
|
"\n",
|
|
"**VisDrone2019-DET** je veřejně dostupný dataset leteckých snímků s anotacemi vozidel.\n",
|
|
"Obsahuje třídy: `pedestrian, people, bicycle, car, van, truck, tricycle, awning-tricycle, bus, motor`.\n",
|
|
"\n",
|
|
"My použijeme pouze vozidlové třídy a převedeme anotace do formátu YOLO.\n",
|
|
"\n",
|
|
"**Citace:**\n",
|
|
"> Zhu, P., Wen, L., Du, D., et al. (2021). Detection and Tracking Meet Drones Challenge. *IEEE TPAMI*."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Note: you may need to restart the kernel to use updated packages.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Instalace závislostí\n",
|
|
"%pip install ultralytics Pillow tqdm requests --quiet"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Stahuji train.zip ...\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from pathlib import Path\n",
|
|
"import shutil, os, zipfile, urllib.request\n",
|
|
"from tqdm.notebook import tqdm\n",
|
|
"\n",
|
|
"DATA_DIR = Path(\"data/visdrone\")\n",
|
|
"DATA_DIR.mkdir(parents=True, exist_ok=True)\n",
|
|
"\n",
|
|
"# VisDrone 2019 DET — stáhni ze stránek http://aiskyeye.com\n",
|
|
"# nebo z Google Drive zrcadla:\n",
|
|
"SPLITS = {\n",
|
|
" \"train\": \"https://github.com/ultralytics/assets/releases/download/v0.0.0/VisDrone2019-DET-train.zip\",\n",
|
|
" \"val\": \"https://github.com/ultralytics/assets/releases/download/v0.0.0/VisDrone2019-DET-val.zip\",\n",
|
|
" \"test\": \"https://github.com/ultralytics/assets/releases/download/v0.0.0/VisDrone2019-DET-test-dev.zip\",\n",
|
|
"}\n",
|
|
"\n",
|
|
"def download_with_progress(url: str, dest: Path):\n",
|
|
" if dest.exists():\n",
|
|
" print(f\" Už existuje: {dest.name}\")\n",
|
|
" return\n",
|
|
" print(f\"Stahuji {dest.name} ...\")\n",
|
|
" urllib.request.urlretrieve(url, dest)\n",
|
|
" print(f\" OK → {dest}\")\n",
|
|
"\n",
|
|
"for split, url in SPLITS.items():\n",
|
|
" zip_path = DATA_DIR / f\"{split}.zip\"\n",
|
|
" download_with_progress(url, zip_path)\n",
|
|
" split_dir = DATA_DIR / split\n",
|
|
" if not split_dir.exists():\n",
|
|
" print(f\"Rozbaluji {zip_path.name} ...\")\n",
|
|
" with zipfile.ZipFile(zip_path) as zf:\n",
|
|
" zf.extractall(DATA_DIR)\n",
|
|
" print(f\" Hotovo → {split_dir}\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Prozkoumání struktury datasetu\n",
|
|
"for split in [\"train\", \"val\", \"test\"]:\n",
|
|
" d = DATA_DIR / split\n",
|
|
" if d.exists():\n",
|
|
" imgs = list(d.glob(\"images/*.jpg\"))\n",
|
|
" anns = list(d.glob(\"annotations/*.txt\"))\n",
|
|
" print(f\"{split:5s}: {len(imgs):4d} snímků, {len(anns):4d} anotací\")\n",
|
|
" else:\n",
|
|
" print(f\"{split}: chybí\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Ukázkový anotační soubor — formát VisDrone:\n",
|
|
"# <bbox_left>,<bbox_top>,<bbox_width>,<bbox_height>,<score>,<category>,<truncation>,<occlusion>\n",
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"sample_ann = next((DATA_DIR / \"train\" / \"annotations\").glob(\"*.txt\"))\n",
|
|
"df = pd.read_csv(sample_ann, header=None,\n",
|
|
" names=[\"x\",\"y\",\"w\",\"h\",\"score\",\"cat\",\"trunc\",\"occ\"])\n",
|
|
"print(f\"Soubor: {sample_ann.name}\")\n",
|
|
"print(df.head(10))\n",
|
|
"print(\"\\nRozdělení tříd v celém souboru:\", df[\"cat\"].value_counts().to_dict())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from PIL import Image\n",
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"# VisDrone kategorie → náš mapovací slovník\n",
|
|
"# 0=ignored, 1=pedestrian, 2=people, 3=bicycle, 4=car,\n",
|
|
"# 5=van, 6=truck, 7=tricycle, 8=awning-tricycle, 9=bus, 10=motor, 11=others\n",
|
|
"\n",
|
|
"# Zachováme jen vozidlové třídy, přemapujeme na 4 naše třídy:\n",
|
|
"# 0=car, 1=van, 2=truck, 3=bus\n",
|
|
"VISDRONE_TO_YOLO = {\n",
|
|
" 4: 0, # car → car\n",
|
|
" 5: 1, # van → van\n",
|
|
" 6: 2, # truck → truck\n",
|
|
" 9: 3, # bus → bus\n",
|
|
"}\n",
|
|
"CLASS_NAMES = [\"car\", \"van\", \"truck\", \"bus\"]\n",
|
|
"\n",
|
|
"YOLO_DIR = Path(\"data/yolo_visdrone\")\n",
|
|
"\n",
|
|
"def convert_split(split: str):\n",
|
|
" src_img = DATA_DIR / split / \"images\"\n",
|
|
" src_ann = DATA_DIR / split / \"annotations\"\n",
|
|
" dst_img = YOLO_DIR / split / \"images\"\n",
|
|
" dst_lbl = YOLO_DIR / split / \"labels\"\n",
|
|
" dst_img.mkdir(parents=True, exist_ok=True)\n",
|
|
" dst_lbl.mkdir(parents=True, exist_ok=True)\n",
|
|
"\n",
|
|
" ann_files = sorted(src_ann.glob(\"*.txt\"))\n",
|
|
" skipped = 0\n",
|
|
"\n",
|
|
" for ann_path in tqdm(ann_files, desc=split):\n",
|
|
" img_path = src_img / ann_path.with_suffix(\".jpg\").name\n",
|
|
" if not img_path.exists():\n",
|
|
" skipped += 1\n",
|
|
" continue\n",
|
|
"\n",
|
|
" img = Image.open(img_path)\n",
|
|
" iw, ih = img.size\n",
|
|
"\n",
|
|
" rows = []\n",
|
|
" with open(ann_path) as f:\n",
|
|
" for line in f:\n",
|
|
" parts = line.strip().split(\",\")\n",
|
|
" if len(parts) < 6:\n",
|
|
" continue\n",
|
|
" x, y, w, h = int(parts[0]), int(parts[1]), int(parts[2]), int(parts[3])\n",
|
|
" cat = int(parts[5])\n",
|
|
" if cat not in VISDRONE_TO_YOLO:\n",
|
|
" continue\n",
|
|
" if w <= 0 or h <= 0:\n",
|
|
" continue\n",
|
|
" yolo_cls = VISDRONE_TO_YOLO[cat]\n",
|
|
" cx = (x + w / 2) / iw\n",
|
|
" cy = (y + h / 2) / ih\n",
|
|
" nw = w / iw\n",
|
|
" nh = h / ih\n",
|
|
" rows.append(f\"{yolo_cls} {cx:.6f} {cy:.6f} {nw:.6f} {nh:.6f}\")\n",
|
|
"\n",
|
|
" # Kopiuj obrázek a ulož label (i prázdný label je OK pro neg. sample)\n",
|
|
" shutil.copy(img_path, dst_img / img_path.name)\n",
|
|
" lbl_out = dst_lbl / ann_path.name\n",
|
|
" lbl_out.write_text(\"\\n\".join(rows))\n",
|
|
"\n",
|
|
" print(f\" {split}: {len(ann_files)-skipped} zpracováno, {skipped} přeskočeno\")\n",
|
|
"\n",
|
|
"for split in [\"train\", \"val\"]:\n",
|
|
" convert_split(split)\n",
|
|
"print(\"Konverze hotova!\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Vytvoření YAML konfigurace pro YOLOv8\n",
|
|
"import yaml\n",
|
|
"\n",
|
|
"cfg = {\n",
|
|
" \"path\": str(YOLO_DIR.resolve()),\n",
|
|
" \"train\": \"train/images\",\n",
|
|
" \"val\": \"val/images\",\n",
|
|
" \"names\": {i: n for i, n in enumerate(CLASS_NAMES)},\n",
|
|
" \"nc\": len(CLASS_NAMES),\n",
|
|
"}\n",
|
|
"\n",
|
|
"yaml_path = YOLO_DIR / \"dataset.yaml\"\n",
|
|
"with open(yaml_path, \"w\") as f:\n",
|
|
" yaml.dump(cfg, f, allow_unicode=True, sort_keys=False)\n",
|
|
"\n",
|
|
"print(f\"Dataset YAML: {yaml_path}\")\n",
|
|
"print(yaml.dump(cfg, allow_unicode=True))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Vizualizace ukázkových anotací\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"import matplotlib.patches as patches\n",
|
|
"import random\n",
|
|
"\n",
|
|
"COLORS = [\"#00FF00\", \"#FFFF00\", \"#FF0000\", \"#0080FF\"] # car, van, truck, bus\n",
|
|
"\n",
|
|
"def show_sample(split=\"train\", n=4):\n",
|
|
" img_dir = YOLO_DIR / split / \"images\"\n",
|
|
" lbl_dir = YOLO_DIR / split / \"labels\"\n",
|
|
" imgs = [p for p in img_dir.glob(\"*.jpg\") if (lbl_dir / p.with_suffix(\".txt\").name).stat().st_size > 0]\n",
|
|
" samples = random.sample(imgs, min(n, len(imgs)))\n",
|
|
"\n",
|
|
" fig, axes = plt.subplots(1, len(samples), figsize=(5*len(samples), 5))\n",
|
|
" if len(samples) == 1:\n",
|
|
" axes = [axes]\n",
|
|
"\n",
|
|
" for ax, img_path in zip(axes, samples):\n",
|
|
" img = Image.open(img_path)\n",
|
|
" iw, ih = img.size\n",
|
|
" ax.imshow(img)\n",
|
|
" lbl_path = lbl_dir / img_path.with_suffix(\".txt\").name\n",
|
|
" for line in lbl_path.read_text().splitlines():\n",
|
|
" if not line.strip():\n",
|
|
" continue\n",
|
|
" cls, cx, cy, nw, nh = map(float, line.split())\n",
|
|
" cls = int(cls)\n",
|
|
" x = (cx - nw/2) * iw\n",
|
|
" y = (cy - nh/2) * ih\n",
|
|
" w = nw * iw\n",
|
|
" h = nh * ih\n",
|
|
" rect = patches.Rectangle((x, y), w, h, linewidth=1.5,\n",
|
|
" edgecolor=COLORS[cls], facecolor=\"none\")\n",
|
|
" ax.add_patch(rect)\n",
|
|
" ax.text(x, y-2, CLASS_NAMES[cls], color=COLORS[cls], fontsize=7)\n",
|
|
" ax.set_title(img_path.stem[:20], fontsize=8)\n",
|
|
" ax.axis(\"off\")\n",
|
|
"\n",
|
|
" plt.suptitle(\"Ukázkové anotace (zelená=car, žlutá=van, červená=truck, modrá=bus)\")\n",
|
|
" plt.tight_layout()\n",
|
|
" plt.savefig(\"sample_annotations.png\", dpi=150, bbox_inches=\"tight\")\n",
|
|
" plt.show()\n",
|
|
"\n",
|
|
"show_sample()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Statistiky datasetu\n",
|
|
"from collections import Counter\n",
|
|
"\n",
|
|
"for split in [\"train\", \"val\"]:\n",
|
|
" lbl_dir = YOLO_DIR / split / \"labels\"\n",
|
|
" counter = Counter()\n",
|
|
" n_imgs = 0\n",
|
|
" for lbl in lbl_dir.glob(\"*.txt\"):\n",
|
|
" lines = [l for l in lbl.read_text().splitlines() if l.strip()]\n",
|
|
" for line in lines:\n",
|
|
" counter[int(line.split()[0])] += 1\n",
|
|
" n_imgs += 1\n",
|
|
" print(f\"\\n{split} ({n_imgs} snímků):\")\n",
|
|
" for cls_id, cnt in sorted(counter.items()):\n",
|
|
" print(f\" {CLASS_NAMES[cls_id]:10s}: {cnt:6d}\")\n",
|
|
" print(f\" {'CELKEM':10s}: {sum(counter.values()):6d}\")"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": ".venv (3.14.4)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.14.4"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|