Junki Ohmura jojonki

## index.html
http://43.4.22.206:8888/<html>
<head>
  <style>
    canvas {
      border: 1px solid black;
    }
  </style>
</head>
<body>
  <canvas id="canvas" width="600" height="400"></canvas>

## covariance_matrix.py
import numpy as np

data = np.array([[40, 35, 80],
                 [80, 50, 90],
                 [20, 55, 40],
                 [94, 80, 88],
                 [90, 30, 100]])
print('Input data (N, featuers):', data, data.shape)
N = data.shape[0]
n_dim = data.shape[1]

## FrozenLake-V0-QLearning-epsilon-greedy.py
# -*- coding: utf-8 -*-
# ref: http://taotao54321.hatenablog.com/entry/2016/11/08/180245

import numpy as np
import gym
from gym import wrappers

# Q learning params
ALPHA = 0.1 # learning rate
GAMMA = 0.99 # reward discount

## init_weights.py
# https://github.com/pytorch/examples/blob/master/dcgan/main.py#L95-L102
def weights_init(m):
    classname = m.__class__.__name__
    if classname.find('Conv') != -1:
        m.weight.data.normal_(0.0, 0.02)
    elif classname.find('BatchNorm') != -1:
        m.weight.data.normal_(1.0, 0.02)
        m.bias.data.fill_(0)


## FrozenLake-V0-QLearning.py
# -*- coding: utf-8 -*-
# ref: https://gym.openai.com/evaluations/eval_1lfzNKEHS9GA7nNWE73w

import numpy as np
import gym
from gym import wrappers

# Q learning params
ALPHA = 0.1 # learning rate
GAMMA = 0.99 # reward discount

## CustomTrainingParams.py
import random
import torch
import torch.nn as nn
from torch.autograd import Variable
from torch import optim
import torch.nn.functional as F

seq_len = 10
n_class = 5
class SimpleNet(nn.Module):

## .direnvrc
activate_conda(){
  eval "$(conda shell.zsh hook)"
  conda activate $1
}

## mac_keybindings.json
// Place your key bindings in this file to override the defaultsauto[]
[
    {
        "key": "ctrl+0",
        "command": "workbench.action.nextEditor"
    },
    {
        "key": "ctrl+9",
        "command": "workbench.action.previousEditor"
    },

## gist:029ec7d6fb2d91038646bb287f7180c6
あああ
ああい
ああう
ああえ
ああお
ああか
ああき
ああく
ああけ
ああこ

## gist:eb158ba2ed7a886b4f555fb2e952188f
   243.2    67.0       1
   254.5    70.1       1
   253.1    59.3       1
   228.1    70.4       1
   240.8    69.5       1
   244.0    69.0       1
   257.9    66.3       1
   255.8    68.3       1
   249.9    63.5       1
   251.3    70.3       1
	http://43.4.22.206:8888/<html>
	<head>
	<style>
	canvas {
	border: 1px solid black;
	}
	</style>
	</head>
	<body>
	<canvas id="canvas" width="600" height="400"></canvas>
	import numpy as np

	data = np.array([[40, 35, 80],
	[80, 50, 90],
	[20, 55, 40],
	[94, 80, 88],
	[90, 30, 100]])
	print('Input data (N, featuers):', data, data.shape)
	N = data.shape[0]
	n_dim = data.shape[1]
	# -- coding: utf-8 --
	# ref: http://taotao54321.hatenablog.com/entry/2016/11/08/180245

	import numpy as np
	import gym
	from gym import wrappers

	# Q learning params
	ALPHA = 0.1 # learning rate
	GAMMA = 0.99 # reward discount
	# https://github.com/pytorch/examples/blob/master/dcgan/main.py#L95-L102
	def weights_init(m):
	classname = m.__class__.__name__
	if classname.find('Conv') != -1:
	m.weight.data.normal_(0.0, 0.02)
	elif classname.find('BatchNorm') != -1:
	m.weight.data.normal_(1.0, 0.02)
	m.bias.data.fill_(0)
	# -- coding: utf-8 --
	# ref: https://gym.openai.com/evaluations/eval_1lfzNKEHS9GA7nNWE73w

	import numpy as np
	import gym
	from gym import wrappers

	# Q learning params
	ALPHA = 0.1 # learning rate
	GAMMA = 0.99 # reward discount
	import random
	import torch
	import torch.nn as nn
	from torch.autograd import Variable
	from torch import optim
	import torch.nn.functional as F

	seq_len = 10
	n_class = 5
	class SimpleNet(nn.Module):
	activate_conda(){
	eval "$(conda shell.zsh hook)"
	conda activate $1
	}
	// Place your key bindings in this file to override the defaultsauto[]
	[
	{
	"key": "ctrl+0",
	"command": "workbench.action.nextEditor"
	},
	{
	"key": "ctrl+9",
	"command": "workbench.action.previousEditor"
	},
	あああ
	ああい
	ああう
	ああえ
	ああお
	ああか
	ああき
	ああく
	ああけ
	ああこ
	243.2 67.0 1
	254.5 70.1 1
	253.1 59.3 1
	228.1 70.4 1
	240.8 69.5 1
	244.0 69.0 1
	257.9 66.3 1
	255.8 68.3 1
	249.9 63.5 1
	251.3 70.3 1