wiseodd

from __future__ import annotations
import warnings

warnings.filterwarnings("ignore")

import torch
from gpytorch.likelihoods import Likelihood
from gpytorch.mlls import ExactMarginalLogLikelihood
from botorch.models.gp_regression import SingleTaskGP
from gpytorch.kernels import Kernel

wiseodd

from collections.abc import MutableMapping
from collections import UserDict
import numpy
import torch
from torch import nn
import torch.utils.data as data_utils

from laplace import Laplace
from laplace.curvature import CurvlinopsGGN, AsdlGGN

wiseodd

from laplace import Laplace
from laplace.curvature import CurvlinopsGGN
import torch
from torch import nn
import torch.utils.data as data_utils
from collections import UserDict
import collections.abc as cols_abc


class Model(nn.Module):

wiseodd

import torch
import tqdm
from transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
tokenizer.pad_token = tokenizer.eos_token
model = GPT2LMHeadModel.from_pretrained('gpt2').to(torch.bfloat16)
assert next(model.parameters()).dtype == torch.bfloat16

input_text = 'Earth is'

wiseodd

import warnings
warnings.filterwarnings('ignore')

import torch
from laplace import Laplace
from helper.dataloaders import get_sinusoid_example
from laplace import Laplace

n_epochs = 1000
torch.manual_seed(711)

wiseodd

wiseodd

import numpy as np
from sklearn.utils import shuffle


# Data comes from y = f(x) = [2, 3].x + [5, 7]
X0 = np.random.randn(100, 2) - 1
X1 = np.random.randn(100, 2) + 1
X = np.vstack([X0, X1])
t = np.vstack([np.zeros([100, 1]), np.ones([100, 1])])

wiseodd

import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import time
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm


plt.ion()
fig = plt.figure()

wiseodd

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
import os


def xavier_init(size):
    in_dim = size[0]

wiseodd

import numpy as np
from sklearn.datasets import make_moons
from sklearn.cross_validation import train_test_split


n_feature = 2
n_class = 2


def make_network(n_hidden=100):