{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "hAyWzMHRd_bW"
},
"source": [
"# Environment setup\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Install Python libraries"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We first pip-install the Python libraries listed in ```requirements.txt```."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"vscode": {
"languageId": "plaintext"
}
},
"outputs": [],
"source": [
"!pip install -r requirements.txt"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Download data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We will download the [SONYC-UST dataset](https://zenodo.org/record/2590742#.XIkTPBNKjuM). The dataset was released along with the following paper (it's probably a good idea to have a look at it):\n",
"\n",
"> Cartwright, M., Mendez, A.E.M., Cramer, J., Lostanlen, V., Dove, G., Wu, H., Salamon, J., Nov, O., Bello, J.P. SONYC Urban Sound Tagging (SONYC-UST): A Multilabel Dataset from an Urban Acoustic Sensor Network. In Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE) , 2019. [PDF](https://dcase.community/documents/workshop2019/proceedings/DCASE2019Workshop_Cartwright_4.pdf)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"root_path = \"/content/drive/My Drive/Enseignement/2023-2024/NumVi/IA-DL/UST_project\"\n",
"ust_data_path = os.path.join(root_path, \"data/ust-data/sonyc-ust\")\n",
"os.makedirs(ust_data_path, exist_ok=True) # create a folder to store the data\n",
"os.makedirs(os.path.join(ust_data_path, 'audio-dev'), exist_ok=True) # create a folder to store the development data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--2024-02-21 13:37:19-- https://zenodo.org/record/3338310/files/annotations.csv\n",
"Resolving zenodo.org (zenodo.org)... 188.184.103.159, 188.185.79.172, 188.184.98.238, ...\n",
"Connecting to zenodo.org (zenodo.org)|188.184.103.159|:443... connected.\n",
"HTTP request sent, awaiting response... 301 MOVED PERMANENTLY\n",
"Location: /records/3338310/files/annotations.csv [following]\n",
"--2024-02-21 13:37:20-- https://zenodo.org/records/3338310/files/annotations.csv\n",
"Reusing existing connection to zenodo.org:443.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 3163972 (3.0M) [text/plain]\n",
"Saving to: ‘annotations.csv’\n",
"\n",
"annotations.csv 100%[===================>] 3.02M 4.17MB/s in 0.7s \n",
"\n",
"2024-02-21 13:37:21 (4.17 MB/s) - ‘annotations.csv’ saved [3163972/3163972]\n",
"\n",
"--2024-02-21 13:37:21-- https://zenodo.org/record/3338310/files/audio-dev.tar.gz\n",
"Resolving zenodo.org (zenodo.org)... 188.184.103.159, 188.185.79.172, 188.184.98.238, ...\n",
"Connecting to zenodo.org (zenodo.org)|188.184.103.159|:443... connected.\n",
"HTTP request sent, awaiting response... 301 MOVED PERMANENTLY\n",
"Location: /records/3338310/files/audio-dev.tar.gz [following]\n",
"--2024-02-21 13:37:21-- https://zenodo.org/records/3338310/files/audio-dev.tar.gz\n",
"Reusing existing connection to zenodo.org:443.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 1892542516 (1.8G) [application/octet-stream]\n",
"Saving to: ‘audio-dev.tar.gz’\n",
"\n",
"audio-dev.tar.gz 100%[===================>] 1.76G 4.84MB/s in 6m 37s \n",
"\n",
"2024-02-21 13:43:59 (4.54 MB/s) - ‘audio-dev.tar.gz’ saved [1892542516/1892542516]\n",
"\n",
"--2024-02-21 13:43:59-- https://zenodo.org/record/3338310/files/audio-eval.tar.gz\n",
"Resolving zenodo.org (zenodo.org)... 188.184.103.159, 188.184.98.238, 188.185.79.172, ...\n",
"Connecting to zenodo.org (zenodo.org)|188.184.103.159|:443... connected.\n",
"HTTP request sent, awaiting response... 301 MOVED PERMANENTLY\n",
"Location: /records/3338310/files/audio-eval.tar.gz [following]\n",
"--2024-02-21 13:44:00-- https://zenodo.org/records/3338310/files/audio-eval.tar.gz\n",
"Reusing existing connection to zenodo.org:443.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 180759660 (172M) [application/octet-stream]\n",
"Saving to: ‘audio-eval.tar.gz’\n",
"\n",
"audio-eval.tar.gz 100%[===================>] 172.39M 20.4MB/s in 8.7s \n",
"\n",
"2024-02-21 13:44:09 (19.7 MB/s) - ‘audio-eval.tar.gz’ saved [180759660/180759660]\n",
"\n",
"--2024-02-21 13:44:09-- https://zenodo.org/record/3338310/files/dcase-ust-taxonomy.yaml\n",
"Resolving zenodo.org (zenodo.org)... 188.184.103.159, 188.184.98.238, 188.185.79.172, ...\n",
"Connecting to zenodo.org (zenodo.org)|188.184.103.159|:443... connected.\n",
"HTTP request sent, awaiting response... 301 MOVED PERMANENTLY\n",
"Location: /records/3338310/files/dcase-ust-taxonomy.yaml [following]\n",
"--2024-02-21 13:44:09-- https://zenodo.org/records/3338310/files/dcase-ust-taxonomy.yaml\n",
"Reusing existing connection to zenodo.org:443.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 1081 (1.1K) [application/octet-stream]\n",
"Saving to: ‘dcase-ust-taxonomy.yaml’\n",
"\n",
"dcase-ust-taxonomy. 100%[===================>] 1.06K 5.24KB/s in 0.2s \n",
"\n",
"2024-02-21 13:44:10 (5.24 KB/s) - ‘dcase-ust-taxonomy.yaml’ saved [1081/1081]\n",
"\n",
"--2024-02-21 13:44:10-- https://zenodo.org/record/3338310/files/README.md\n",
"Resolving zenodo.org (zenodo.org)... 188.184.103.159, 188.184.98.238, 188.185.79.172, ...\n",
"Connecting to zenodo.org (zenodo.org)|188.184.103.159|:443... connected.\n",
"HTTP request sent, awaiting response... 301 MOVED PERMANENTLY\n",
"Location: /records/3338310/files/README.md [following]\n",
"--2024-02-21 13:44:11-- https://zenodo.org/records/3338310/files/README.md\n",
"Reusing existing connection to zenodo.org:443.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 8716 (8.5K) [application/octet-stream]\n",
"Saving to: ‘README.md’\n",
"\n",
"README.md 100%[===================>] 8.51K --.-KB/s in 0.004s \n",
"\n",
"2024-02-21 13:44:11 (2.26 MB/s) - ‘README.md’ saved [8716/8716]\n",
"\n"
]
}
],
"source": [
"os.chdir(ust_data_path)\n",
"!wget https://zenodo.org/record/3338310/files/annotations.csv\n",
"!wget https://zenodo.org/record/3338310/files/audio-dev.tar.gz\n",
"!wget https://zenodo.org/record/3338310/files/audio-eval.tar.gz\n",
"!wget https://zenodo.org/record/3338310/files/dcase-ust-taxonomy.yaml\n",
"!wget https://zenodo.org/record/3338310/files/README.md\n",
"os.chdir(\"audio-dev\")\n",
"!tar xf ../audio-dev.tar.gz\n",
"os.chdir(\"..\")\n",
"!rm audio-dev.tar.gz\n",
"!tar xf audio-eval.tar.gz\n",
"!rm audio-eval.tar.gz\n",
"os.chdir(root_path)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You should end-up with the following file structure:"
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"```\n",
"data\n",
"+-- ust-data\n",
"| +-- sonyc-ust\n",
"| | +-- audio-dev\n",
"| | | +-- train\n",
"| | | | +-- 01_000006.wav\n",
"| | | | +-- ...\n",
"| | | +-- validate\n",
"| | | | +-- 00_000066.wav\n",
"| | | | +-- ...\n",
"| | +-- audio-eval\n",
"| | | +-- 00_010346.wav\n",
"| | | +-- ...\n",
"| | +-- annotations.csv\n",
"| | +-- dcase-ust-taxonomy.yaml\n",
"| | +-- README.md\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"vscode": {
"languageId": "plaintext"
}
},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.14"
}
},
"nbformat": 4,
"nbformat_minor": 1
}