Kyle Kastner kastnerkyle

## semantic_search_with_gzip.py
import gzip

def gzip_search(query: str, candidate_chunks: list[str], top_k: int=1):
    """
    文字列ベースで類似したテキストチャンクを推定するアルゴリズム.
    `query`, `chunk`, および`query + " " + chunk`をそれぞれgzipで圧縮し、編集距離のようなものをベースに評価する.

    Parameters:
        query (str): 検索クエリとして使用する文字列.
        top_k (int, optional): 返される類似チャンクの上位k個を指定する (default: 1).

## find_noise.py
import torch
import k_diffusion as K

from PIL import Image
from torch import autocast
from einops import rearrange, repeat

def pil_img_to_latent(model, img, batch_size=1, device='cuda', half=True):
    init_image = pil_img_to_torch(img, half=half).to(device)
    init_image = repeat(init_image, '1 ... -> b ...', b=batch_size)

## adamw_finetune.py
import math
import torch
from torch import optim


class AdamWFinetune(optim.Optimizer):
    r"""Implements AdamW algorithm with optional weight decay toward the starting value, to
    prevent overfitting to the new dataset during fine-tuning.

    The original Adam algorithm was proposed in `Adam: A Method for Stochastic Optimization`_.

## Kiritan singing voice synthesis demo.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                kastnerkyle
                / Kiritan singing voice synthesis demo.ipynb
            
            
              Created
              May 3, 2020 06:09
                — forked from r9y9/Kiritan singing voice synthesis demo.ipynb
            
              
                Neural_network_based_singing_voice_synthesis_demo_using_kiritan_singing_database_(Japanese)
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## make_audiobook.py
#!/usr/bin/env python3
"""
To use:
1. install/set-up the google cloud api and dependencies listed on https://github.com/GoogleCloudPlatform/python-docs-samples/tree/master/texttospeech/cloud-client
2. install pandoc and pypandoc, also tqdm
3. create and download a service_account.json ("Service account key") from https://console.cloud.google.com/apis/credentials
4. run GOOGLE_APPLICATION_CREDENTIALS=service_account.json python make_audiobook.py book_name.epub
"""
import re
import sys

## make_audiobook.py
#!/usr/bin/env python3
"""
To use:
1. install/set-up the google cloud api and dependencies listed on https://github.com/GoogleCloudPlatform/python-docs-samples/tree/master/texttospeech/cloud-client
2. install pandoc and pypandoc, also tqdm
3. create and download a service_account.json ("Service account key") from https://console.cloud.google.com/apis/credentials
4. run GOOGLE_APPLICATION_CREDENTIALS=service_account.json python make_audiobook.py book_name.epub
"""
import re
import sys

## newsci-headlines
Some planets may orbit a supermassive black hole instead of a star
This is almost certainly not what Denisovans looked like
UN climate summit: Scientists' messages to world leaders
A hat that zaps the scalp with electricity helps reverse male balding
Man sees the world in miniature after a stroke damages his brain
Do dads matter? Anna Machin on the fascinating science of fatherhood
People like the idea of a carbon tax - if the money is put to good use
Climate change will boost risk of extreme flooding in northern Europe
Fast swimming fish robot could perform underwater surveillance
Ad Astra: Pirates and space monkeys can't save dull space psychodrama

## pytorch-glumpy.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              2 stars
            
          
                kastnerkyle
                / pytorch-glumpy.md
            
            
              Created
              March 4, 2020 22:45
                — forked from victor-shepardson/pytorch-glumpy.md
            
              
                using pycuda and glumpy to draw pytorch GPU tensors to the screen without copying to host memory
              
          
    Code

https://gist.github.com/victor-shepardson/5b3d3087dc2b4817b9bffdb8e87a57c4
Setup

I'm using Ubuntu 16.04 with a GTX 1060
install CUDA


## exact_pg.py
import jax
import jax.numpy as np
from jax import grad, jit
from jax.scipy.special import logsumexp


def dadashi_fig2d():
    """ Figure 2 d) of
    ''The Value Function Polytope in Reinforcement Learning''
    by Dadashi et al. (2019) https://arxiv.org/abs/1901.11524

## gpt-2-wikitext-103.py
# Copyright (c) 2019-present, Thomas Wolf.
# All rights reserved. This source code is licensed under the MIT-style license.
""" A very small and self-contained gist to train a GPT-2 transformer model on wikitext-103 """
import os
from collections import namedtuple
from tqdm import tqdm
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
from ignite.engine import Engine, Events
	import gzip

	def gzip_search(query: str, candidate_chunks: list[str], top_k: int=1):
	"""
	文字列ベースで類似したテキストチャンクを推定するアルゴリズム.
	`query`, `chunk`, および`query + " " + chunk`をそれぞれgzipで圧縮し、編集距離のようなものをベースに評価する.

	Parameters:
	query (str): 検索クエリとして使用する文字列.
	top_k (int, optional): 返される類似チャンクの上位k個を指定する (default: 1).
	import torch
	import k_diffusion as K

	from PIL import Image
	from torch import autocast
	from einops import rearrange, repeat

	def pil_img_to_latent(model, img, batch_size=1, device='cuda', half=True):
	init_image = pil_img_to_torch(img, half=half).to(device)
	init_image = repeat(init_image, '1 ... -> b ...', b=batch_size)
	import math
	import torch
	from torch import optim


	class AdamWFinetune(optim.Optimizer):
	r"""Implements AdamW algorithm with optional weight decay toward the starting value, to
	prevent overfitting to the new dataset during fine-tuning.

	The original Adam algorithm was proposed in `Adam: A Method for Stochastic Optimization`_.
	#!/usr/bin/env python3
	"""
	To use:
	1. install/set-up the google cloud api and dependencies listed on https://github.com/GoogleCloudPlatform/python-docs-samples/tree/master/texttospeech/cloud-client
	2. install pandoc and pypandoc, also tqdm
	3. create and download a service_account.json ("Service account key") from https://console.cloud.google.com/apis/credentials
	4. run GOOGLE_APPLICATION_CREDENTIALS=service_account.json python make_audiobook.py book_name.epub
	"""
	import re
	import sys
	Some planets may orbit a supermassive black hole instead of a star
	This is almost certainly not what Denisovans looked like
	UN climate summit: Scientists' messages to world leaders
	A hat that zaps the scalp with electricity helps reverse male balding
	Man sees the world in miniature after a stroke damages his brain
	Do dads matter? Anna Machin on the fascinating science of fatherhood
	People like the idea of a carbon tax - if the money is put to good use
	Climate change will boost risk of extreme flooding in northern Europe
	Fast swimming fish robot could perform underwater surveillance
	Ad Astra: Pirates and space monkeys can't save dull space psychodrama
	import jax
	import jax.numpy as np
	from jax import grad, jit
	from jax.scipy.special import logsumexp


	def dadashi_fig2d():
	""" Figure 2 d) of
	''The Value Function Polytope in Reinforcement Learning''
	by Dadashi et al. (2019) https://arxiv.org/abs/1901.11524
	# Copyright (c) 2019-present, Thomas Wolf.
	# All rights reserved. This source code is licensed under the MIT-style license.
	""" A very small and self-contained gist to train a GPT-2 transformer model on wikitext-103 """
	import os
	from collections import namedtuple
	from tqdm import tqdm
	import torch
	import torch.nn as nn
	from torch.utils.data import DataLoader
	from ignite.engine import Engine, Events