{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Image task notebook template\n",
"## Loading the necessary libraries"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"from fastapi import APIRouter\n",
"from datetime import datetime\n",
"from datasets import load_dataset\n",
"from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
"\n",
"import random\n",
"\n",
"import sys\n",
"sys.path.append('../')\n",
"\n",
"from tasks.utils.evaluation import ImageEvaluationRequest\n",
"from tasks.utils.emissions import tracker, clean_emissions_data, get_space_info\n",
"from tasks.image import parse_boxes,compute_iou,compute_max_iou"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Loading the datasets and splitting them"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4f62b23ca587477d9f37430e687bf951",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"README.md: 0%| | 0.00/7.72k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\theo.alvesdacosta\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:139: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\theo.alvesdacosta\\.cache\\huggingface\\hub\\datasets--pyronear--pyro-sdis. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
"To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
" warnings.warn(message)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "70735dd748e343119b5a7cd966dcd0f0",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"train-00000-of-00007.parquet: 0%| | 0.00/433M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "903c3227c24649f1a0424e039d74d303",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"train-00001-of-00007.parquet: 0%| | 0.00/434M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8795b7696f124715b9d52287d5cd4ee0",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"train-00002-of-00007.parquet: 0%| | 0.00/432M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4b6c1240bf024d61bf913584d13834f5",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"train-00003-of-00007.parquet: 0%| | 0.00/428M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "cd5f8172a31f4fd79d489db96ede9c21",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"train-00004-of-00007.parquet: 0%| | 0.00/431M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "416af82dba3a4ab7ad13190703c90757",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"train-00005-of-00007.parquet: 0%| | 0.00/429M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6819ad85508641a1a64bea34303446ac",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"train-00006-of-00007.parquet: 0%| | 0.00/431M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "90a7f85c802b4330b502c8bbd3cca7f9",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"val-00000-of-00001.parquet: 0%| | 0.00/407M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b93f2f19aafb43e2b8db0fd7bb3ebd34",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Generating train split: 0%| | 0/29537 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c14c0f2cde184c959970dfccaa26b2d2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Generating val split: 0%| | 0/4099 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"request = ImageEvaluationRequest()\n",
"\n",
"# Load and prepare the dataset\n",
"dataset = load_dataset(request.dataset_name)\n",
"\n",
"# Split dataset\n",
"train_test = dataset[\"train\"]\n",
"test_dataset = dataset[\"val\"]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Random Baseline"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"# Start tracking emissions\n",
"tracker.start()\n",
"tracker.start_task(\"inference\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"\n",
"#--------------------------------------------------------------------------------------------\n",
"# YOUR MODEL INFERENCE CODE HERE\n",
"# Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.\n",
"#-------------------------------------------------------------------------------------------- \n",
"\n",
"# Make random predictions (placeholder for actual model inference)\n",
"\n",
"predictions = []\n",
"true_labels = []\n",
"pred_boxes = []\n",
"true_boxes_list = [] # List of lists, each inner list contains boxes for one image\n",
"\n",
"for example in test_dataset:\n",
" # Parse true annotation (YOLO format: class_id x_center y_center width height)\n",
" annotation = example.get(\"annotations\", \"\").strip()\n",
" has_smoke = len(annotation) > 0\n",
" true_labels.append(int(has_smoke))\n",
" \n",
" # Make random classification prediction\n",
" pred_has_smoke = random.random() > 0.5\n",
" predictions.append(int(pred_has_smoke))\n",
" \n",
" # If there's a true box, parse it and make random box prediction\n",
" if has_smoke:\n",
" # Parse all true boxes from the annotation\n",
" image_true_boxes = parse_boxes(annotation)\n",
" true_boxes_list.append(image_true_boxes)\n",
" \n",
" # For baseline, make one random box prediction per image\n",
" # In a real model, you might want to predict multiple boxes\n",
" random_box = [\n",
" random.random(), # x_center\n",
" random.random(), # y_center\n",
" random.random() * 0.5, # width (max 0.5)\n",
" random.random() * 0.5 # height (max 0.5)\n",
" ]\n",
" pred_boxes.append(random_box)\n",
"\n",
"\n",
"#--------------------------------------------------------------------------------------------\n",
"# YOUR MODEL INFERENCE STOPS HERE\n",
"#-------------------------------------------------------------------------------------------- "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Stop tracking emissions\n",
"emissions_data = tracker.stop_task()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"# Calculate classification metrics\n",
"classification_accuracy = accuracy_score(true_labels, predictions)\n",
"classification_precision = precision_score(true_labels, predictions)\n",
"classification_recall = recall_score(true_labels, predictions)\n",
"\n",
"# Calculate mean IoU for object detection (only for images with smoke)\n",
"# For each image, we compute the max IoU between the predicted box and all true boxes\n",
"ious = []\n",
"for true_boxes, pred_box in zip(true_boxes_list, pred_boxes):\n",
" max_iou = compute_max_iou(true_boxes, pred_box)\n",
" ious.append(max_iou)\n",
"\n",
"mean_iou = float(np.mean(ious)) if ious else 0.0"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'submission_timestamp': '2025-01-22T15:57:37.288173',\n",
" 'classification_accuracy': 0.5001692620176033,\n",
" 'classification_precision': 0.8397129186602871,\n",
" 'classification_recall': 0.4972677595628415,\n",
" 'mean_iou': 0.002819781629108398,\n",
" 'energy_consumed_wh': 0.779355299496116,\n",
" 'emissions_gco2eq': 0.043674291628462855,\n",
" 'emissions_data': {'run_id': '4e750cd5-60f0-444c-baee-b5f7b31f784b',\n",
" 'duration': 51.72819679998793,\n",
" 'emissions': 4.3674291628462856e-05,\n",
" 'emissions_rate': 8.445163379568943e-07,\n",
" 'cpu_power': 42.5,\n",
" 'gpu_power': 0.0,\n",
" 'ram_power': 11.755242347717285,\n",
" 'cpu_energy': 0.0006104993474311617,\n",
" 'gpu_energy': 0,\n",
" 'ram_energy': 0.00016885595206495442,\n",
" 'energy_consumed': 0.0007793552994961161,\n",
" 'country_name': 'France',\n",
" 'country_iso_code': 'FRA',\n",
" 'region': 'île-de-france',\n",
" 'cloud_provider': '',\n",
" 'cloud_region': '',\n",
" 'os': 'Windows-11-10.0.22631-SP0',\n",
" 'python_version': '3.12.7',\n",
" 'codecarbon_version': '3.0.0_rc0',\n",
" 'cpu_count': 12,\n",
" 'cpu_model': '13th Gen Intel(R) Core(TM) i7-1365U',\n",
" 'gpu_count': None,\n",
" 'gpu_model': None,\n",
" 'ram_total_size': 31.347312927246094,\n",
" 'tracking_mode': 'machine',\n",
" 'on_cloud': 'N',\n",
" 'pue': 1.0},\n",
" 'dataset_config': {'dataset_name': 'pyronear/pyro-sdis',\n",
" 'test_size': 0.2,\n",
" 'test_seed': 42}}"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"# Prepare results dictionary\n",
"results = {\n",
" \"submission_timestamp\": datetime.now().isoformat(),\n",
" \"classification_accuracy\": float(classification_accuracy),\n",
" \"classification_precision\": float(classification_precision),\n",
" \"classification_recall\": float(classification_recall),\n",
" \"mean_iou\": mean_iou,\n",
" \"energy_consumed_wh\": emissions_data.energy_consumed * 1000,\n",
" \"emissions_gco2eq\": emissions_data.emissions * 1000,\n",
" \"emissions_data\": clean_emissions_data(emissions_data),\n",
" \"dataset_config\": {\n",
" \"dataset_name\": request.dataset_name,\n",
" \"test_size\": request.test_size,\n",
" \"test_seed\": request.test_seed\n",
" }\n",
"}\n",
"results"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}