Shamimul Islam Shamim-38

I am masters student.

Shamim-38 / Video2Frames_in_Colab.py

Created April 17, 2023 09:18

	from google.colab import drive
	drive.mount('/content/drive', force_remount=True)


	# Importing all necessary libraries
	import cv2
	import os

	# Read the video from specified path
	cam = cv2.VideoCapture("Video/Path/h.mp4") #Video path

Shamim-38 / split_into_training_gallery-probe.py

Created March 28, 2023 11:17

Data Preprocessing for Authentication/Verification


	from sklearn.model_selection import train_test_split
	import numpy as np


	a = ["1", "3", "4", "1", "3", "4"]
	b = [[2, 4, 3],[0, 4, 5], [8, 9, 5], [5, 4, 5],[8, 4, 5], [2, 9, 5]]
	y_train = np.array(a)
	x_train = np.array(b)

Shamim-38 / gist:1a2d557d9c06163e8f7a302a77d08ecc

Created December 3, 2022 12:17

Resizing_Video.sh

	Pretty good solution. One can resize a video as:
	ffmpeg -i AigCblw--hk_000067_000077.mp4 -vf "scale='if(gt(ih,iw),256,trunc(oha/2)2):if(gt(ih,iw),trunc(ow/a/2)*2,256)'" output.mp4

	For multiple videos, one can perform (please mkdir a videos_resized folder in prepath ../):
	for f in .mp4 ; do ffmpeg -i "$f" -vf "scale='if(gt(ih,iw),256,trunc(oha/2)2):if(gt(ih,iw),trunc(ow/a/2)2,256)'" "../videos_resized/$f" ; done

Shamim-38 / Try to find max in list

Created October 23, 2022 05:53

	Try to find max in list:

	l = [1,2,3,4,4]
	num = max(l, key=lambda x:l.count(x)) # num will be 4

	the you can get the count of num.

	l.count(num) # this wil returns 2

	in the other hand as @buddemat said(Here), it is better to:

Shamim-38 / reduce Video size in Ubuntu

Created October 22, 2022 19:01

	To reduce the size of your mp4 you have two good choices with FFmpeg:

	Experiment with Constant Rate Factor (CRF) settings to find a match between video output size and video quality
	Experiment with the set bitrate of your choice and use a 2 pass encode.

	Details of both below:

	1. Resize using FFmpeg's Constant Rate Factor (CRF) option:

	In FFmpeg the CRF settings vary from 0-51 with 0 being lossless and 51 being shockingly poor quality. The default is 23 and you need to find the 'sweet spot' for your particular video of file size and video quality with some experimentation.

Shamim-38 / keras_model_continue_training.ipynb

Created September 25, 2022 19:05

Keras_model_Continue_training.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

Shamim-38 / Decision Tree

Created January 26, 2022 02:41

	import numpy as np
	import pandas as pd
	eps = np.finfo(float).eps
	from numpy import log2 as log

	dataset = {'Taste':['Salty','Spicy','Spicy','Spicy','Spicy','Sweet','Salty','Sweet','Spicy','Salty'],
	'Temperature':['Hot','Hot','Hot','Cold','Hot','Cold','Cold','Hot','Cold','Hot'],
	'Texture':['Soft','Soft','Hard','Hard','Hard','Soft','Soft','Soft','Soft','Hard'],
	'Eat':['No','No','Yes','No','Yes','Yes','No','Yes','Yes','Yes']}

Shamim-38 / auto_encoder.py

Created December 5, 2021 07:24

	import tensorflow as tf
	import numpy as np
	import matplotlib.pyplot as plt
	#%matplotlib inline
	from tensorflow.keras.datasets import fashion_mnist

	#(x_train, _), (x_test, _) = fashion_mnist.load_data()

	import os

Shamim-38 / KeyPoint_extraction.py

Created December 5, 2021 07:24

	#Writer: Md Shamimul Islam

	import cv2
	import numpy as np
	import os
	from matplotlib import pyplot as plt
	import time
	import mediapipe as mp

	import glob

Shamim-38 / local repository to github

Created October 10, 2020 07:15

	Create a new repository on GitHub. You can also add a gitignore file, a readme and a licence if you want
	Open Git Bash
	Change the current working directory to your local project.
	Initialize the local directory as a Git repository.
	git init
	Add the files in your new local repository. This stages them for the first commit.
	git add .
	Commit the files that you’ve staged in your local repository.
	git commit -m "initial commit"
	Copy the https url of your newly created repo