Skip to content

Instantly share code, notes, and snippets.

@schollz

schollz/deep_dreams_music_video.ipynb

Last active April 18, 2024 14:49
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save schollz/1741ac03a19750fadef7e5cd0add0f29 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save schollz/1741ac03a19750fadef7e5cd0add0f29 to your computer and use it in GitHub Desktop.
Download ZIP
aimovie.ipynb
Display the source blob
Display the rendered blob
Raw
deep_dreams_music_video.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "aimovie.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyMuRxejHQKRMZaBDHNJeLVM",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/schollz/1741ac03a19750fadef7e5cd0add0f29/aimovie.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "S4IkNuc_Z5wx",
"outputId": "53dd9078-dfae-4c13-91f3-04b586efabd6"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: tqdm in /usr/local/lib/python3.7/dist-packages (4.63.0)\n",
"Requirement already satisfied: librosa in /usr/local/lib/python3.7/dist-packages (0.8.1)\n",
"Requirement already satisfied: moviepy in /usr/local/lib/python3.7/dist-packages (0.2.3.5)\n",
"Requirement already satisfied: torch in /usr/local/lib/python3.7/dist-packages (1.10.0+cu111)\n",
"Collecting scipy==1.1.0\n",
" Downloading scipy-1.1.0-cp37-cp37m-manylinux1_x86_64.whl (31.2 MB)\n",
"\u001b[K |████████████████████████████████| 31.2 MB 22.8 MB/s \n",
"\u001b[?25hCollecting pytorch_pretrained_biggan\n",
" Downloading pytorch_pretrained_biggan-0.1.1-py3-none-any.whl (27 kB)\n",
"Requirement already satisfied: numpy>=1.8.2 in /usr/local/lib/python3.7/dist-packages (from scipy==1.1.0) (1.21.5)\n",
"Requirement already satisfied: audioread>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from librosa) (2.1.9)\n",
"Requirement already satisfied: numba>=0.43.0 in /usr/local/lib/python3.7/dist-packages (from librosa) (0.51.2)\n",
"Requirement already satisfied: pooch>=1.0 in /usr/local/lib/python3.7/dist-packages (from librosa) (1.6.0)\n",
"Requirement already satisfied: soundfile>=0.10.2 in /usr/local/lib/python3.7/dist-packages (from librosa) (0.10.3.post1)\n",
"Requirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.7/dist-packages (from librosa) (1.1.0)\n",
"Requirement already satisfied: scikit-learn!=0.19.0,>=0.14.0 in /usr/local/lib/python3.7/dist-packages (from librosa) (1.0.2)\n",
"Requirement already satisfied: decorator>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from librosa) (4.4.2)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.7/dist-packages (from librosa) (21.3)\n",
"Requirement already satisfied: resampy>=0.2.2 in /usr/local/lib/python3.7/dist-packages (from librosa) (0.2.2)\n",
"Requirement already satisfied: llvmlite<0.35,>=0.34.0.dev0 in /usr/local/lib/python3.7/dist-packages (from numba>=0.43.0->librosa) (0.34.0)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from numba>=0.43.0->librosa) (57.4.0)\n",
"Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging>=20.0->librosa) (3.0.7)\n",
"Requirement already satisfied: appdirs>=1.3.0 in /usr/local/lib/python3.7/dist-packages (from pooch>=1.0->librosa) (1.4.4)\n",
"Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.7/dist-packages (from pooch>=1.0->librosa) (2.23.0)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.10)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (1.24.3)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (3.0.4)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2021.10.8)\n",
"Requirement already satisfied: six>=1.3 in /usr/local/lib/python3.7/dist-packages (from resampy>=0.2.2->librosa) (1.15.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn!=0.19.0,>=0.14.0->librosa) (3.1.0)\n",
"Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.7/dist-packages (from soundfile>=0.10.2->librosa) (1.15.0)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.7/dist-packages (from cffi>=1.0->soundfile>=0.10.2->librosa) (2.21)\n",
"Requirement already satisfied: imageio<3.0,>=2.1.2 in /usr/local/lib/python3.7/dist-packages (from moviepy) (2.4.1)\n",
"Requirement already satisfied: pillow in /usr/local/lib/python3.7/dist-packages (from imageio<3.0,>=2.1.2->moviepy) (7.1.2)\n",
"Requirement already satisfied: typing-extensions in /usr/local/lib/python3.7/dist-packages (from torch) (3.10.0.2)\n",
"Collecting boto3\n",
" Downloading boto3-1.21.22-py3-none-any.whl (132 kB)\n",
"\u001b[K |████████████████████████████████| 132 kB 27.8 MB/s \n",
"\u001b[?25hCollecting jmespath<2.0.0,>=0.7.1\n",
" Downloading jmespath-1.0.0-py3-none-any.whl (23 kB)\n",
"Collecting botocore<1.25.0,>=1.24.22\n",
" Downloading botocore-1.24.22-py3-none-any.whl (8.6 MB)\n",
"\u001b[K |████████████████████████████████| 8.6 MB 19.1 MB/s \n",
"\u001b[?25hCollecting s3transfer<0.6.0,>=0.5.0\n",
" Downloading s3transfer-0.5.2-py3-none-any.whl (79 kB)\n",
"\u001b[K |████████████████████████████████| 79 kB 3.6 MB/s \n",
"\u001b[?25hCollecting urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1\n",
" Downloading urllib3-1.25.11-py2.py3-none-any.whl (127 kB)\n",
"\u001b[K |████████████████████████████████| 127 kB 33.5 MB/s \n",
"\u001b[?25hRequirement already satisfied: python-dateutil<3.0.0,>=2.1 in /usr/local/lib/python3.7/dist-packages (from botocore<1.25.0,>=1.24.22->boto3->pytorch_pretrained_biggan) (2.8.2)\n",
"Installing collected packages: urllib3, jmespath, botocore, scipy, s3transfer, boto3, pytorch-pretrained-biggan\n",
" Attempting uninstall: urllib3\n",
" Found existing installation: urllib3 1.24.3\n",
" Uninstalling urllib3-1.24.3:\n",
" Successfully uninstalled urllib3-1.24.3\n",
" Attempting uninstall: scipy\n",
" Found existing installation: scipy 1.4.1\n",
" Uninstalling scipy-1.4.1:\n",
" Successfully uninstalled scipy-1.4.1\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"pymc3 3.11.4 requires scipy>=1.2.0, but you have scipy 1.1.0 which is incompatible.\n",
"plotnine 0.6.0 requires scipy>=1.2.0, but you have scipy 1.1.0 which is incompatible.\n",
"jax 0.3.1 requires scipy>=1.2.1, but you have scipy 1.1.0 which is incompatible.\n",
"datascience 0.10.6 requires folium==0.2.1, but you have folium 0.8.3 which is incompatible.\n",
"albumentations 0.1.12 requires imgaug<0.2.7,>=0.2.5, but you have imgaug 0.2.9 which is incompatible.\u001b[0m\n",
"Successfully installed boto3-1.21.22 botocore-1.24.22 jmespath-1.0.0 pytorch-pretrained-biggan-0.1.1 s3transfer-0.5.2 scipy-1.1.0 urllib3-1.25.11\n"
]
}
],
"source": [
"pip install tqdm librosa moviepy torch scipy==1.1.0 pytorch_pretrained_biggan"
]
},
{
"cell_type": "code",
"source": [
"import librosa\n",
"import argparse\n",
"import numpy as np\n",
"import moviepy.editor as mpy\n",
"import random\n",
"import torch\n",
"from scipy.misc import toimage\n",
"from tqdm import tqdm\n",
"from pytorch_pretrained_biggan import (BigGAN, one_hot_from_names, truncated_noise_sample,\n",
" save_as_images, display_in_terminal)\n",
"\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Wbx5M7-7aJuz",
"outputId": "2c8a5453-df40-45ab-f64c-05661e30e21d"
},
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Imageio: 'ffmpeg-linux64-v3.3.1' was not found on your computer; downloading it now.\n",
"Try 1. Download from https://github.com/imageio/imageio-binaries/raw/master/ffmpeg/ffmpeg-linux64-v3.3.1 (43.8 MB)\n",
"Downloading: 8192/45929032 bytes (0.0%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b1073152/45929032 bytes (2.3%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b3194880/45929032 bytes (7.0%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b4571136/45929032 bytes (10.0%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b5906432/45929032 bytes (12.9%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b7798784/45929032 bytes (17.0%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b9682944/45929032 bytes (21.1%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b11550720/45929032 bytes (25.1%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b12730368/45929032 bytes (27.7%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b14409728/45929032 bytes (31.4%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b16572416/45929032 bytes (36.1%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b18341888/45929032 bytes (39.9%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b19963904/45929032 bytes (43.5%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b22257664/45929032 bytes (48.5%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b24051712/45929032 bytes (52.4%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b25296896/45929032 bytes (55.1%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b27385856/45929032 bytes (59.6%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b29253632/45929032 bytes (63.7%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b30949376/45929032 bytes (67.4%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b32219136/45929032 bytes (70.1%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b34045952/45929032 bytes (74.1%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b35979264/45929032 bytes (78.3%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b37421056/45929032 bytes (81.5%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b39256064/45929032 bytes (85.5%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b41009152/45929032 bytes (89.3%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b43319296/45929032 bytes (94.3%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b45023232/45929032 bytes (98.0%)\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b45929032/45929032 bytes (100.0%)\n",
" Done\n",
"File saved as /root/.imageio/ffmpeg/ffmpeg-linux64-v3.3.1.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"from google.colab import files\n",
"\n",
"uploaded = files.upload()\n",
"\n",
"for fn in uploaded.keys():\n",
" print('User uploaded file \"{name}\" with length {length} bytes'.format(\n",
" name=fn, length=len(uploaded[fn])))\n",
" "
],
"metadata": {
"colab": {
"resources": {
"http://localhost:8080/nbextensions/google.colab/files.js": {
"data": "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",
"ok": true,
"headers": [
[
"content-type",
"application/javascript"
]
],
"status": 200,
"status_text": "OK"
}
},
"base_uri": "https://localhost:8080/",
"height": 92
},
"id": "T9jpnFY9ate5",
"outputId": "2e6d390c-be0b-416f-e432-f46f5f691c93"
},
"execution_count": 3,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"\n",
" <input type=\"file\" id=\"files-54ce7932-a622-43a0-8af2-e0c0db9686f0\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-54ce7932-a622-43a0-8af2-e0c0db9686f0\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script src=\"/nbextensions/google.colab/files.js\"></script> "
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Saving 1.mp3 to 1.mp3\n",
"User uploaded file \"1.mp3\" with length 640749 bytes\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"with open('/tmp/1.mp3', 'wb') as writefile:\n",
" writefile.write(uploaded[\"1.mp3\"])\n",
"\n",
"y, sr = librosa.load('/tmp/1.mp3')\n",
"\n",
"# set model name based on resolution\n",
"model_name = \"biggan-deep-256\" # -128, -256, or -512\n",
"\n",
"frame_length = 512\n",
"\n",
"# set pitch sensitivity\n",
"set_pitch_sensitivity = 150\n",
"pitch_sensitivity = (300 - set_pitch_sensitivity) * 512 / frame_length\n",
"\n",
"# set tempo sensitivity\n",
"set_sensitivity = 0.25\n",
"tempo_sensitivity = set_sensitivity * frame_length / 512\n",
"\n",
"# set depth\n",
"depth = 1\n",
"\n",
"# set number of classes\n",
"num_classes = 12\n",
"\n",
"# set sort_classes_by_power\n",
"sort_classes_by_power = 0\n",
"\n",
"# set jitter\n",
"jitter = 0.5\n",
"\n",
"# set truncation\n",
"truncation = 1\n",
"\n",
"# set batch size\n",
"batch_size = 30\n",
"\n",
"# set use_previous_classes\n",
"use_previous_vectors = 0\n",
"\n",
"# set use_previous_vectors\n",
"use_previous_classes = 0\n",
"\n",
"# set output name\n",
"outname = '/tmp/1.mp4'\n",
"\n",
"smooth_factor = int(20 * 512 / frame_length)\n",
"frame_lim = int(np.floor(len(y) / sr * 22050 / frame_length / batch_size))\n",
"\n",
"# Load pre-trained model\n",
"model = BigGAN.from_pretrained(model_name)\n",
"\n",
"# set device\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"\n",
"\n",
"########################################\n",
"########################################\n",
"########################################\n",
"########################################\n",
"########################################\n",
"\n",
"\n",
"# create spectrogram\n",
"spec = librosa.feature.melspectrogram(\n",
" y=y, sr=sr, n_mels=128, fmax=8000, hop_length=frame_length\n",
")\n",
"\n",
"# get mean power at each time point\n",
"specm = np.mean(spec, axis=0)\n",
"\n",
"# compute power gradient across time points\n",
"gradm = np.gradient(specm)\n",
"\n",
"# set max to 1\n",
"gradm = gradm / np.max(gradm)\n",
"\n",
"# set negative gradient time points to zero\n",
"gradm = gradm.clip(min=0)\n",
"\n",
"# normalize mean power between 0-1\n",
"specm = (specm - np.min(specm)) / np.ptp(specm)\n",
"\n",
"# create chromagram of pitches X time points\n",
"chroma = librosa.feature.chroma_cqt(y=y, sr=sr, hop_length=frame_length)\n",
"\n",
"# sort pitches by overall power\n",
"chromasort = np.argsort(np.mean(chroma, axis=1))[::-1]\n",
"\n",
"cls1000 = list(range(1000))\n",
"random.shuffle(cls1000)\n",
"classes = cls1000[:12]\n",
"\n",
"\n",
"if sort_classes_by_power == 1:\n",
" classes = [classes[s] for s in np.argsort(chromasort[:num_classes])]\n",
"\n",
"\n",
"# initialize first class vector\n",
"cv1 = np.zeros(1000)\n",
"for pi, p in enumerate(chromasort[:num_classes]):\n",
"\n",
" if num_classes < 12:\n",
" cv1[classes[pi]] = chroma[p][\n",
" np.min([np.where(chrow > 0)[0][0] for chrow in chroma])\n",
" ]\n",
" else:\n",
" cv1[classes[p]] = chroma[p][\n",
" np.min([np.where(chrow > 0)[0][0] for chrow in chroma])\n",
" ]\n",
"\n",
"# initialize first noise vector\n",
"nv1 = truncated_noise_sample(truncation=truncation)[0]\n",
"\n",
"# initialize list of class and noise vectors\n",
"class_vectors = [cv1]\n",
"noise_vectors = [nv1]\n",
"\n",
"# initialize previous vectors (will be used to track the previous frame)\n",
"cvlast = cv1\n",
"nvlast = nv1\n",
"\n",
"\n",
"# initialize the direction of noise vector unit updates\n",
"update_dir = np.zeros(128)\n",
"for ni, n in enumerate(nv1):\n",
" if n < 0:\n",
" update_dir[ni] = 1\n",
" else:\n",
" update_dir[ni] = -1\n",
"\n",
"\n",
"# initialize noise unit update\n",
"update_last = np.zeros(128)\n",
"\n",
"# get new jitters\n",
"def new_jitters(jitter):\n",
" jitters = np.zeros(128)\n",
" for j in range(128):\n",
" if random.uniform(0, 1) < 0.5:\n",
" jitters[j] = 1\n",
" else:\n",
" jitters[j] = 1 - jitter\n",
" return jitters\n",
"\n",
"\n",
"# get new update directions\n",
"def new_update_dir(nv2, update_dir):\n",
" for ni, n in enumerate(nv2):\n",
" if n >= 2 * truncation - tempo_sensitivity:\n",
" update_dir[ni] = -1\n",
"\n",
" elif n < -2 * truncation + tempo_sensitivity:\n",
" update_dir[ni] = 1\n",
" return update_dir\n",
"\n",
"\n",
"# smooth class vectors\n",
"def smooth(class_vectors, smooth_factor):\n",
"\n",
" if smooth_factor == 1:\n",
" return class_vectors\n",
"\n",
" class_vectors_terp = []\n",
" for c in range(int(np.floor(len(class_vectors) / smooth_factor) - 1)):\n",
" ci = c * smooth_factor\n",
" cva = np.mean(class_vectors[int(ci) : int(ci) + smooth_factor], axis=0)\n",
" cvb = np.mean(\n",
" class_vectors[int(ci) + smooth_factor : int(ci) + smooth_factor * 2], axis=0\n",
" )\n",
"\n",
" for j in range(smooth_factor):\n",
" cvc = cva * (1 - j / (smooth_factor - 1)) + cvb * (j / (smooth_factor - 1))\n",
" class_vectors_terp.append(cvc)\n",
"\n",
" return np.array(class_vectors_terp)\n",
"\n",
"\n",
"# normalize class vector between 0-1\n",
"def normalize_cv(cv2):\n",
" min_class_val = min(i for i in cv2 if i != 0)\n",
" for ci, c in enumerate(cv2):\n",
" if c == 0:\n",
" cv2[ci] = min_class_val\n",
" cv2 = (cv2 - min_class_val) / np.ptp(cv2)\n",
"\n",
" return cv2\n",
"\n",
"\n",
"print(\"\\nGenerating input vectors \\n\")\n",
"\n",
"for i in tqdm(range(len(gradm))):\n",
"\n",
" # print progress\n",
" pass\n",
"\n",
" # update jitter vector every 100 frames by setting ~half of noise vector units to lower sensitivity\n",
" if i % 200 == 0:\n",
" jitters = new_jitters(jitter)\n",
"\n",
" # get last noise vector\n",
" nv1 = nvlast\n",
"\n",
" # set noise vector update based on direction, sensitivity, jitter, and combination of overall power and gradient of power\n",
" update = (\n",
" np.array([tempo_sensitivity for k in range(128)])\n",
" * (gradm[i] + specm[i])\n",
" * update_dir\n",
" * jitters\n",
" )\n",
"\n",
" # smooth the update with the previous update (to avoid overly sharp frame transitions)\n",
" update = (update + update_last * 3) / 4\n",
"\n",
" # set last update\n",
" update_last = update\n",
"\n",
" # update noise vector\n",
" nv2 = nv1 + update\n",
"\n",
" # append to noise vectors\n",
" noise_vectors.append(nv2)\n",
"\n",
" # set last noise vector\n",
" nvlast = nv2\n",
"\n",
" # update the direction of noise units\n",
" update_dir = new_update_dir(nv2, update_dir)\n",
"\n",
" # get last class vector\n",
" cv1 = cvlast\n",
"\n",
" # generate new class vector\n",
" cv2 = np.zeros(1000)\n",
" for j in range(num_classes):\n",
"\n",
" cv2[classes[j]] = (\n",
" cvlast[classes[j]] + ((chroma[chromasort[j]][i]) / (pitch_sensitivity))\n",
" ) / (1 + (1 / ((pitch_sensitivity))))\n",
"\n",
" # if more than 6 classes, normalize new class vector between 0 and 1, else simply set max class val to 1\n",
" if num_classes > 6:\n",
" cv2 = normalize_cv(cv2)\n",
" else:\n",
" cv2 = cv2 / np.max(cv2)\n",
"\n",
" # adjust depth\n",
" cv2 = cv2 * depth\n",
"\n",
" # this prevents rare bugs where all classes are the same value\n",
" if np.std(cv2[np.where(cv2 != 0)]) < 0.0000001:\n",
" cv2[classes[0]] = cv2[classes[0]] + 0.01\n",
"\n",
" # append new class vector\n",
" class_vectors.append(cv2)\n",
"\n",
" # set last class vector\n",
" cvlast = cv2\n",
"\n",
"\n",
"# interpolate between class vectors of bin size [smooth_factor] to smooth frames\n",
"class_vectors = smooth(class_vectors, smooth_factor)\n",
"\n",
"\n",
"# check whether to use vectors from last run\n",
"if use_previous_vectors == 1:\n",
" # load vectors from previous run\n",
" class_vectors = np.load(\"/tmp/class_vectors.npy\")\n",
" noise_vectors = np.load(\"/tmp/noise_vectors.npy\")\n",
"else:\n",
" # save record of vectors for current video\n",
" np.save(\"/tmp/class_vectors.npy\", class_vectors)\n",
" np.save(\"/tmp/noise_vectors.npy\", noise_vectors)\n",
"\n",
"# convert to Tensor\n",
"noise_vectors = torch.Tensor(np.array(noise_vectors))\n",
"class_vectors = torch.Tensor(np.array(class_vectors))\n",
"\n",
"\n",
"# Generate frames in batches of batch_size\n",
"\n",
"print(\"\\n\\nGenerating frames \\n\")\n",
"\n",
"# send to CUDA if running on GPU\n",
"model = model.to(device)\n",
"noise_vectors = noise_vectors.to(device)\n",
"class_vectors = class_vectors.to(device)\n",
"\n",
"\n",
"frames = []\n",
"\n",
"for i in tqdm(range(frame_lim)):\n",
"\n",
" # print progress\n",
" pass\n",
"\n",
" if (i + 1) * batch_size > len(class_vectors):\n",
" torch.cuda.empty_cache()\n",
" break\n",
"\n",
" # get batch\n",
" noise_vector = noise_vectors[i * batch_size : (i + 1) * batch_size]\n",
" class_vector = class_vectors[i * batch_size : (i + 1) * batch_size]\n",
"\n",
" # Generate images\n",
" with torch.no_grad():\n",
" output = model(noise_vector, class_vector, truncation)\n",
"\n",
" output_cpu = output.cpu().data.numpy()\n",
"\n",
" # convert to image array and add to frames\n",
" for out in output_cpu:\n",
" im = np.array(toimage(out))\n",
" frames.append(im)\n",
"\n",
" # empty cuda cache\n",
" torch.cuda.empty_cache()\n",
"\n",
"aud = mpy.AudioFileClip(\"/tmp/1.mp3\", fps=44100)\n",
"clip = mpy.ImageSequenceClip(frames, fps=22050 / frame_length)\n",
"clip = clip.set_audio(aud)\n",
"clip.write_videofile(outname, audio_codec=\"aac\")\n",
"\n",
"from google.colab import files\n",
"\n",
"files.download('/tmp/1.mp4')\n",
"\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 330
},
"id": "wbwY0W7lb4Gu",
"outputId": "c73bd8e3-a236-4018-fc52-d00f24e33b07"
},
"execution_count": 15,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"Generating input vectors \n",
"\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"100%|██████████| 1723/1723 [00:03<00:00, 517.78it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"\n",
"Generating frames \n",
"\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 98%|█████████▊| 56/57 [02:21<00:02, 2.53s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"[MoviePy] >>>> Building video /tmp/1.mp4\n",
"[MoviePy] Writing audio in 1TEMP_MPY_wvf_snd.mp4\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n",
"100%|██████████| 883/883 [00:01<00:00, 456.69it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"[MoviePy] Done.\n",
"[MoviePy] Writing video /tmp/1.mp4\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n",
"100%|██████████| 1680/1680 [00:16<00:00, 98.96it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"[MoviePy] Done.\n",
"[MoviePy] >>>> Video ready: /tmp/1.mp4 \n",
"\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.Javascript object>"
],
"application/javascript": [
"\n",
" async function download(id, filename, size) {\n",
" if (!google.colab.kernel.accessAllowed) {\n",
" return;\n",
" }\n",
" const div = document.createElement('div');\n",
" const label = document.createElement('label');\n",
" label.textContent = `Downloading \"${filename}\": `;\n",
" div.appendChild(label);\n",
" const progress = document.createElement('progress');\n",
" progress.max = size;\n",
" div.appendChild(progress);\n",
" document.body.appendChild(div);\n",
"\n",
" const buffers = [];\n",
" let downloaded = 0;\n",
"\n",
" const channel = await google.colab.kernel.comms.open(id);\n",
" // Send a message to notify the kernel that we're ready.\n",
" channel.send({})\n",
"\n",
" for await (const message of channel.messages) {\n",
" // Send a message to notify the kernel that we're ready.\n",
" channel.send({})\n",
" if (message.buffers) {\n",
" for (const buffer of message.buffers) {\n",
" buffers.push(buffer);\n",
" downloaded += buffer.byteLength;\n",
" progress.value = downloaded;\n",
" }\n",
" }\n",
" }\n",
" const blob = new Blob(buffers, {type: 'application/binary'});\n",
" const a = document.createElement('a');\n",
" a.href = window.URL.createObjectURL(blob);\n",
" a.download = filename;\n",
" div.appendChild(a);\n",
" a.click();\n",
" div.remove();\n",
" }\n",
" "
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.Javascript object>"
],
"application/javascript": [
"download(\"download_719ef4ee-4925-434d-b8ca-cecc5dcce6db\", \"1.mp4\", 5747919)"
]
},
"metadata": {}
}
]
}
]
}
@fzedde
Copy link

fzedde commented Apr 17, 2024 •
edited
Loading

Hello, i cant seem to run the second section. The run of the first section ends with a few warning messages:
Any suggestion?
-thanks so much for your work

Building wheels for collected packages: scipy, moviepy
error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.
Building wheel for scipy (setup.py) ... error
ERROR: Failed building wheel for scipy
Running setup.py clean for scipy
error: subprocess-exited-with-error

× python setup.py clean did not run successfully.
│ exit code: 1
╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed cleaning build dir for scipy
Building wheel for moviepy (setup.py) ... done
Created wheel for moviepy: filename=moviepy-1.0.3-py3-none-any.whl size=110721 sha256=0b86af3d230dfc8ad2aead606230fa1c06de5eff890714bfdc18fb0916e2f04e
Stored in directory: /root/.cache/pip/wheels/96/32/2d/e10123bd88fbfc02fed53cc18c80a171d3c87479ed845fa7c1
Successfully built moviepy
Failed to build scipy
ERROR: Could not build wheels for scipy, which is required to install pyproject.toml-based projects
[3]
0 s
import librosa
import argparse
import numpy as np
import moviepy.editor as mpy
import random
import torch
from scipy.misc import toimage
from tqdm import tqdm
from pytorch_pretrained_biggan import (BigGAN, one_hot_from_names, truncated_noise_sample,
save_as_images, display_in_terminal)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment