| """ | |
| stable diffusion dreaming | |
| creates hypnotic moving videos by smoothly walking randomly through the sample space | |
| example way to run this script: | |
| $ python stablediffusionwalk.py --prompt "blueberry spaghetti" --name blueberry | |
| to stitch together the images, e.g.: | |
| $ ffmpeg -r 10 -f image2 -s 512x512 -i blueberry/frame%06d.jpg -vcodec libx264 -crf 10 -pix_fmt yuv420p blueberry.mp4 |
| from glob import glob | |
| # Creates a video from a folder containing images of training progress | |
| # Allows sampling the image less often as iterations increase | |
| # (Requires images be sortable by filename for now. Could use modification date too) | |
| def render_video(output_path="/content/taming-transformers/output.mp4", src_path="/content/taming-transformers/", file_glob="*.png", step_increase_every=100): | |
| tmp_path = "/tmp/latentvisions_tmp" | |
| files = glob(src_path+file_glob) | |
| files.sort() |
See the RLE section for definition of RLE format.
This class expects the (extended) RLE input to be correctly formatted. It is a two state parser, thus multi-state RLE will not parse properly.
The output this.pattern is a string with spaces(dead)/zero(alive)
with lines separated by '\n'.
This article aims at explaining lambda calculus in a more approachable less 'mathy' manner.
Memoization: Memoization is an optimization technique used primarily to speed up computer programs by caching the result of expensive function calls and returning the cached result when fed with the same input.
Pure Function: A pure function is a function whose computation does not depend on globally declared variables, it does no I/O or mutations. All it does is return a value after doing a bunch of computations on the arguments it recieves. For a given set of arguments, a pure function will always return the same value. Thus, a pure function is one that is memoizable.
| cqt_filter_fft = librosa.constantq.__cqt_filter_fft | |
| class PseudoCqt(): | |
| """A class to compute pseudo-CQT with Pytorch. | |
| Written by Keunwoo Choi | |
| API (+implementations) follows librosa (https://librosa.github.io/librosa/generated/librosa.core.pseudo_cqt.html) | |
| Usage: | |
| src, _ = librosa.load(filename) | |
| src_tensor = torch.tensor(src) |
| dataset | meta data | contents | with audio |
|---|---|---|---|
| 200DrumMachines | 7371 one-shots | yes | |
| AAM | onsets, pitches, instruments, melody instrument, keys, chords, tempo, beats | 3000 (artificial) tracks | yes |
| ACM_MIRUM | tempo | 1410 excerpts (60s) | yes |
| ACPAS | aligned audio and scores | 2189 performances of 497 scores | downloadable |
| AcousticBrainz-Genre | 15-31 genres with 265-745 subgenres | audio features for over 2000000 songs | no |
| #!/bin/bash | |
| TEXT_RESET='\e[0m' | |
| TEXT_YELLOW='\e[1;33m' | |
| wget https://developer.nvidia.com/compute/cuda/9.2/Prod2/local_installers/cuda-repo-ubuntu1604-9-2-local_9.2.148-1_amd64 | |
| echo -e $TEXT_YELLOW | |
| echo 'WEBGET finished..' | |
| echo -e $TEXT_RESET |
| import keras.backend as K | |
| import tensorflow as tf | |
| from tensorflow.keras.layers import Layer | |
| """Not tested, I'll play around with GANs soon with it.""" | |
| from tensorflow.keras.layers import Conv2D | |
| import numpy as np | |
| class CoordConv2D(Layer): |
| from tensorflow.python.layers import base | |
| import tensorflow as tf | |
| class AddCoords(base.Layer): | |
| """Add coords to a tensor""" | |
| def __init__(self, x_dim=64, y_dim=64, with_r=False): | |
| super(AddCoords, self).__init__() | |
| self.x_dim = x_dim | |
| self.y_dim = y_dim |