kor01

Applicability:

	1. model compilation requires implementation of compute output shape
    
    2. model compilation requires homogeneous training data tensor shapes
    
    3. model internal attributes is set by passing a defer tensor through model call
    
	4. model compilation is more akin to tf graph mode

kor01

import vtk
# The colors module defines various useful colors.
from vtk.util.colors import tomato

cylinder = vtk.vtkCylinderSource()

# the side of the cylinder is made up with 100 edges polygon
cylinder.SetResolution(100)

kor01

# cmake for opengl projects

cmake_minimum_required(VERSION 3.12)
project(opengl_stuffs)

set(CMAKE_CXX_STANDARD 11)

find_package(OpenGL)
find_package(GLUT)
find_package(GLEW)

kor01

% show current assumptions
syms z
assumptions(z)

% set assumptions
syms x
assume(x >= 0)

% add assumptions
assumeAlso(x,'integer')

kor01

%save my_useful_session 10-20 23

kor01

import numpy as np
import cv2
import matplotlib.pyplot as plt
import matplotlib.image as mpimg

image = mpimg.imread('bbox-example-image.jpg')

# Define a function that takes an image, a list of bounding boxes, 
# and optional color tuple and line thickness as inputs
# then draws boxes in that color on the output

kor01

hold on
plot(x(1, :), x(2,:))

kor01

Definition and Conventions:

• kinmematics frame of each link is infered rather than defined in urdf

• each joint position and orientation is defined relative to it's parents kinematics frame

• the parent kinematics frame is defined as the frame of it's parent joint

• the kinematics frame of root link is eye(4)

kor01

depth = number of channel
path / kernel = [depth, convolutional sliding window weight]

sliding window weight = [height, width, depth], where depth equals to previous image channels

feature map_i = output[i, :, :] the ith layer of the output hyper image after convolution
stride = number of pixels when shifting the kernel window
valid_padding = stop slide at the edge (without padding)
same_padding = pad with zeros to make output image the same as input

kor01

in conventional notations:

1. layer input = the tensor before activation

2. layer output = the tensor after activation

3. next layer input = this layer output transformed by the edges

4. delta_layer = dLoss / dlayer_input