ugo-nama-kun

from os import makedirs

import wandb
import pandas as pd
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

# 保存ディレクトリ名を指定 (Exist_ok)

ugo-nama-kun

import torch
import torchvision
import random
import matplotlib.pyplot as plt

class MNISTHandler:
    def __init__(self, train=True):
        """
        Initializes the MNIST dataset.

ugo-nama-kun

import matplotlib.pyplot as plt
import numpy as np

n_bins = 100


def get_dist(center, scale, bins):
    dist = np.ones(bins)
    s_list = [15, 10, 5, 2]
    power_list = [10, 20, 40, 50]

ugo-nama-kun

# from : https://twitter.com/karpathy/status/1610822271157022720?s=20&t=kEsA7YdbLhb7bMqg_PUxww

import code; code.interact(local=locals())

# something you want to check...

ugo-nama-kun

class BetaHead(nn.Module):
    def __init__(self, in_features, action_size):
        super(BetaHead, self).__init__()

        self.fcc_c0 = nn.Linear(in_features, action_size)
        nn.init.orthogonal_(self.fcc_c0.weight, gain=0.01)
        nn.init.zeros_(self.fcc_c0.bias)

        self.fcc_c1 = nn.Linear(in_features, action_size)
        nn.init.orthogonal_(self.fcc_c1.weight, gain=0.01)

ugo-nama-kun

import torchvision.transforms as transforms
import matplotlib.pyplot as plt

from torch.utils.data import DataLoader
from torchvision.datasets import MNIST

mnist_data = MNIST('./mnist', train=True, download=True, transform=transforms.ToTensor())
data_loader = DataLoader(mnist_data, batch_size=4, shuffle=False)
data_iter = iter(data_loader)

ugo-nama-kun

def deconvsize(w_in, k, stride, pad, output_pad):
	return (w_in - 1) * stride - 2 * pad + k + output_pad

ugo-nama-kun

# Run by : python get_parser.py --seed 0 --gpu -1

import argparser

# argparser
parser = argparse.ArgumentParser(description="When RL, something similar like...")

parser.add_argument("--seed", help="Seed value. An Int value", type=int, required=True)
parser.add_argument("--gpu", help="GPU ID", type=int, default=-1)
parser.add_argument("--group", help="Run group, like 'Apr19'", default="test", type=str)

ugo-nama-kun

import torch
import torch.nn as nn
import torch.nn.functional as F


class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

ugo-nama-kun

import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0, 2, 10)
y = np.linspace(2, 0, 10)
err = 0.1 + np.random.rand(len(x)) * 0.3
angle = np.random.rand(len(x)) * np.pi / 3

plt.figure(figsize=(2, 2), dpi=300)
for i in range(len(x)):