Mukhesh P S mukheshpugal

I hereby claim:

To claim this, I am signing this object:

	class Exp_SE3(Function):
	"""
	Implements exp SO3 as a torch fuction
	"""

	@staticmethod
	def forward(ctx, vec: "Tensor[6]") -> "Tensor[4,4]":
	"""
	:param ctx: context, to store some tensors
	for backward

	import numpy as np
	import pptk
	from mayavi import mlab
	import cv2

	depthmap = np.array(cv2.imread('depth.png',0));
	depthmap = depthmap[300:340, 220:260]
	intrinsics = np.array([[525.0, 0, 319.5],
	[0, 525.0, 239.5],
	[0, 0, 1]])

	def matrix_from_euler(euler):
	rotation_x = torch.tensor([[1, 0, 0], [0, torch.cos(euler[0]), -torch.sin(euler[0])], [0, torch.sin(euler[0]), torch.cos(euler[0])]])
	rotation_y = torch.tensor([[torch.cos(euler[1]), 0, torch.sin(euler[1])], [0, 1, 0], [-torch.sin(euler[1]), 0, torch.cos(euler[1])]])
	rotation_z = torch.tensor([[torch.cos(euler[2]), -torch.sin(euler[2]), 0], [torch.sin(euler[2]), torch.cos(euler[2]), 0], [0, 0, 1]])

	rotation_3d = torch.matmul(torch.matmul(rotation_x, rotation_y), rotation_z)

	return rotation_3d

	from scipy.optimize import least_squares as ls
	import math
	import numpy as np
	from PIL import Image
	import cv2
	from matplotlib import pyplot as plt

	def huber(r, delta):
	if math.sqrt(r) < delta:
	return r / (2 * delta)