🚶‍♂️ MotionGPT: Human Motion
as Foreign Language

MotionGPT consists of a motion tokenizer responsible for converting raw motion data into discrete motion tokens, as well as a motion-aware language model that learns to understand the motion tokens from large language pre-training models by corresponding textual descriptions.

⏩ Project: https://motion-gpt.github.io/

🖥 Github: https://github.com/openmotionlab/motiongpt

📕 Paper: https://arxiv.org/pdf/2306.14795.pdf

🔗Dataset: https://paperswithcode.com/dataset/amass

https://t.iss.one/DataScienceT

🖥 Free Courses on Large Language Models

▪ChatGPT Prompt Engineering for Developers

▪LangChain for LLM Application Development

▪Building Systems with the ChatGPT API

▪Google Cloud Generative AI Learning Path

▪Introduction to Large Language Models with Google Cloud

▪LLM University

▪Full Stack LLM Bootcamp

https://t.iss.one/DataScienceT

PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation

🖥 Github: https://github.com/jieqianyu/panet

⏩ Paper: https://arxiv.org/pdf/2306.15348v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/kitti

https://t.iss.one/DataScienceT

💬 3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement

A large-scale speech corpus to facilitate the research of speech representation

🖥 Github: https://github.com/alibaba-damo-academy/3D-Speaker

📕 Paper: https://arxiv.org/abs/2306.15354v1

🔗Dataset: https://3dspeaker.github.io/

https://t.iss.one/DataScienceT

What the Brain Sees

How a text-to-image model generates images from brain scans

https://www.deeplearning.ai/the-batch/how-a-text-to-image-model-generates-images-from-brain-scans/

https://t.iss.one/DataScienceT

The source code for DragGAN has been released! 🔥🔥🔥

We can finally play with that marvel!

🔗 GitHub repository: https://github.com/XingangPan/DragGAN

https://t.iss.one/DataScienceT

📕 Constrained-Text-Generation-Studio

AI writing assistant for recreational linguists, poets, creative writers, and/or researchers to use and study the ability of large-scale language models.

🖥 Github: https://github.com/hellisotherpeople/constrained-text-generation-studio

📕 Paper: https://arxiv.org/abs/2306.15926v1

🔗Dataset: https://huggingface.co/datasets/Hellisotherpeople/Lipogram-e

https://t.iss.one/DataScienceT

CellViT: Vision Transformers for Precise Cell Segmentation and Classification

🖥 Github: https://github.com/tio-ikim/cellvit

⏩ Paper: https://arxiv.org/pdf/2306.15350v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/pannuke

https://t.iss.one/DataScienceT

A special and important channel to download the most important books to learn programming and data science

t.iss.one/DataScienceM

💬 GLIGEN: Open-Set Grounded Text-to-Image Generation

GLIGEN’s zero-shot performance on COCO and LVIS outperforms that of existing supervised layout-to-image baselines by a large margin. Code comming soon.

⭐️ Project: https://gligen.github.io/

⭐️ Demo: https://aka.ms/gligen

✅️ Paper: https://arxiv.org/abs/2301.07093

🖥 Github: https://github.com/gligen/GLIGEN

https://t.iss.one/DataScienceT

🖥 RL4CO

🖥 Github: https://github.com/kaist-silab/rl4co

📕 Paper: https://arxiv.org/abs/2306.17100v1

🖥 Colab: https://colab.research.google.com/github/kaist-silab/rl4co/blob/main/notebooks/1-quickstart.ipynb

https://t.iss.one/DataScienceT

🧍‍♂ BEDLAM: Bodies Exhibiting Detailed Lifelike Animated Motion

BEDLAM is useful for a variety of tasks and all images, ground truth bodies, 3D clothing, support code, and more are available for research purposes.

🖥 Github: https://github.com/pixelite1201/BEDLAM

📕 Paper: https://bedlam.is.tuebingen.mpg.de/media/upload/BEDLAM_CVPR2023.pdf

🔗Render code: https://github.com/PerceivingSystems/bedlam_render

🎞 Video: https://youtu.be/OBttHFwdtfI

👑 Dataset: https://paperswithcode.com/dataset/bedlam

https://t.iss.one/DataScienceT

Python Machine Learning Projects (2023)

Download Book ✓:
https://t.iss.one/DataScienceM/240

⭐️ ManimML: Communicating Machine Learning Architectures with Animation

An open-source Python library for easily generating animations of ML algorithms directly from code.

from manim_ml.neural_network import NeuralNetwork, Convolutional2DLayer, FeedForwardLayer
# Make nn
nn = NeuralNetwork([
Convolutional2DLayer(1, 7, filter_spacing=0.32),
Convolutional2DLayer(3, 5, 3, filter_spacing=0.32, activation_function="ReLU"),
FeedForwardLayer(3, activation_function="Sigmoid"),
],
layer_spacing=0.25,
)
self.add(nn)
# Play animation
forward_pass = nn.make_forward_pass_animation()
self.play(forward_pass)

🖥 Github: https://github.com/helblazer811/manimml

📕 Paper: https://arxiv.org/abs/2306.17108v1

📌 Project: https://www.manim.community/

https://t.iss.one/DataScienceT

🧬NeuralFuse

🖥 Github: https://github.com/ibm/neuralfuse

⏩ Paper: https://arxiv.org/pdf/2306.16869v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/imagenet

https://t.iss.one/DataScienceT

🖥 10 Advanced Python Scripts For Everyday Programming

1. SpeedTest with Python
# pip install pyspeedtest
# pip install speedtest
# pip install speedtest-cli

#method 1
import speedtest

speedTest = speedtest.Speedtest()
print(speedTest.get_best_server())

#Check download speed
print(speedTest.download())

#Check upload speed
print(speedTest.upload())

# Method 2

import pyspeedtest
st = pyspeedtest.SpeedTest()
st.ping()
st.download()
st.upload()

2. Search on Google
# pip install google

from googlesearch import search

query = "Medium.com"

for url in search(query):
print(url)

3. Make Web Bot
# pip install selenium

import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys

bot = webdriver.Chrome("chromedriver.exe")
bot.get('[https://www.google.com'](https://www.google.com'))

search = bot.find_element_by_name('q')
search.send_keys("@codedev101")
search.send_keys(Keys.RETURN)
time.sleep(5)
bot.quit()

4. Fetch Song Lyrics
# pip install lyricsgenius

import lyricsgenius

api_key = "xxxxxxxxxxxxxxxxxxxxx"

genius = lyricsgenius.Genius(api_key)
artist = genius.search_artist("Pop Smoke", max_songs=5,sort="title")
song = artist.song("100k On a Coupe")

print(song.lyrics)

5. Get Exif Data of Photos
# Get Exif of Photo

# Method 1
# pip install pillow
import PIL.Image
import PIL.ExifTags

img = PIL.Image.open("Img.jpg")
exif_data =
{
PIL.ExifTags.TAGS[i]: j
for i, j in img._getexif().items()
if i in PIL.ExifTags.TAGS
}
print(exif_data)


# Method 2
# pip install ExifRead
import exifread

filename = open(path_name, 'rb')

tags = exifread.process_file(filename)
print(tags)

6. OCR Text from Image
# pip install pytesseract

import pytesseract
from PIL import Image

pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'

t=Image.open("img.png")
text = pytesseract.image_to_string(t, config='')

print(text)

7. Convert Photo into Cartonize
# pip install opencv-python

import cv2

img = cv2.imread('img.jpg')
grayimg = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
grayimg = cv2.medianBlur(grayimg, 5)

edges = cv2.Laplacian(grayimg , cv2.CV_8U, ksize=5)
r,mask =cv2.threshold(edges,100,255,cv2.THRESH_BINARY_INV)

img2 = cv2.bitwise_and(img, img, mask=mask)
img2 = cv2.medianBlur(img2, 5)

cv2.imwrite("cartooned.jpg", mask)

8. Empty Recycle Bin
# pip install winshell

import winshell
try:
winshell.recycle_bin().empty(confirm=False, /show_progress=False, sound=True)
print("Recycle bin is emptied Now")
except:
print("Recycle bin already empty")

9. Python Image Enhancement
# pip install pillow

from PIL import Image,ImageFilter
from PIL import ImageEnhance

im = Image.open('img.jpg')

# Choose your filter
# add Hastag at start if you don't want to any filter below

en = ImageEnhance.Color(im)
en = ImageEnhance.Contrast(im)
en = ImageEnhance.Brightness(im)
en = ImageEnhance.Sharpness(im)

# result
en.enhance(1.5).show("enhanced")

10. Get Window Version
# Window Version

import wmi
data = wmi.WMI()
for os_name in data.Win32_OperatingSystem():
print(os_name.Caption) # Microsoft Windows 11 Home

https://t.iss.one/DataScienceT

📶 Extract Saved WiFi Passwords in Python

import subprocess
import os
import re
from collections import namedtuple
import configparser

def get_linux_saved_wifi_passwords(verbose=1):


network_connections_path = "/etc/NetworkManager/system-connections/"
fields = ["ssid", "auth-alg", "key-mgmt", "psk"]
Profile = namedtuple("Profile", [f.replace("-", "_") for f in fields])
profiles = []
for file in os.listdir(network_connections_path):
data = { k.replace("-", "_"): None for k in fields }
config = configparser.ConfigParser()
config.read(os.path.join(network_connections_path, file))
for _, section in config.items():
for k, v in section.items():
if k in fields:
data[k.replace("-", "_")] = v
profile = Profile(**data)
if verbose >= 1:
print_linux_profile(profile)
profiles.append(profile)
return profiles


def print_linux_profiles(verbose):
"""Prints all extracted SSIDs along with Key (PSK) on Linux"""
print("SSID AUTH KEY-MGMT PSK")
print("-"*50)
get_linux_saved_wifi_passwords(verbose)

https://t.iss.one/DataScienceT

🖥 5 useful Python automation scripts

1. Download Youtube videos
pip install pytube

from pytube import YouTube

# Specify the URL of the YouTube video
video_url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"

# Create a YouTube object
yt = YouTube(video_url)

# Select the highest resolution stream
stream = yt.streams.get_highest_resolution()

# Define the output path for the downloaded video
output_path = "path/to/output/directory/"

# Download the video
stream.download(output_path)

print("Video downloaded successfully!")

2. Automate WhatsApp messages

pip install pywhatkit

import pywhatkit

# Set the target phone number (with country code) and the message
phone_number = "+1234567890"
message = "Hello, this is an automated WhatsApp message!"

# Schedule the message to be sent at a specific time (24-hour format)
hour = 13
minute = 30

# Send the scheduled message
pywhatkit.sendwhatmsg(phone_number, message, hour, minute)

3. Google search with Python

pip install googlesearch-python

from googlesearch import search

# Define the query you want to search
query = "Python programming"

# Specify the number of search results you want to retrieve
num_results = 5

# Perform the search and retrieve the results
search_results = search(query, num_results=num_results, lang='en')

# Print the search results
for result in search_results:
print(result)

4. Download Instagram posts

pip install instaloader

import instaloader

# Create an instance of Instaloader
loader = instaloader.Instaloader()

# Define the target Instagram profile
target_profile = "instagram"

# Download posts from the profile
loader.download_profile(target_profile, profile_pic=False, fast_update=True)

print("Posts downloaded successfully!")

5. Extract audio from video files

pip install moviepy

from moviepy.editor import VideoFileClip

# Define the path to the video file
video_path = "path/to/video/file.mp4"

# Create a VideoFileClip object
video_clip = VideoFileClip(video_path)

# Extract the audio from the video
audio_clip = video_clip.audio

# Define the output audio file path
output_audio_path = "path/to/output/audio/file.mp3"

# Write the audio to the output file
audio_clip.write_audiofile(output_audio_path)

# Close the clips
video_clip.close()
audio_clip.close()

print("Audio extracted successfully!")

https://t.iss.one/DataScienceT

🚀 NAUTILUS: boosting Bayesian importance nested sampling with deep learning

A novel approach to boost the efficiency of the importance nested sampling (INS) technique for Bayesian posterior and evidence estimation using deep learning.

Install:
pip install nautilus-sampler

import corner
import numpy as np
from nautilus import Prior, Sampler
from scipy.stats import multivariate_normal

prior = Prior()
for key in 'abc':
prior.add_parameter(key)

def likelihood(param_dict):
x = [param_dict[key] for key in 'abc']
return multivariate_normal.logpdf(x, mean=[0.4, 0.5, 0.6], cov=0.01)

sampler = Sampler(prior, likelihood)
sampler.run(verbose=True)
points, log_w, log_l = sampler.posterior()
corner.corner(points, weights=np.exp(log_w), labels='abc')

🖥 Github: https://github.com/johannesulf/nautilus

⭐️ Docs: https://nautilus-sampler.readthedocs.io/

📕 Paper: https://arxiv.org/abs/2306.16923v1

https://t.iss.one/DataScienceT

🏌️ GlOttal-flow LPC Filter (GOLF)

A DDSP-based neural vocoder.

🖥 Github: https://github.com/yoyololicon/golf

📕 Paper: https://arxiv.org/abs/2306.17252v1

🔗Demo: https://yoyololicon.github.io/golf-demo/

https://t.iss.one/DataScienceT

🔮 SAM-PT: Segment Anything + Tracking 🔮

⭐️ SAM-PT is the first method to utilize sparse point propagation for Video Object Segmentation (VOS).

🌐 Review https://t.ly/QLMG

🌐 Paper arxiv.org/pdf/2307.01197.pdf

🌐 Project www.vis.xyz/pub/sam-pt/

🌐 Code github.com/SysCV/sam-pt

https://t.iss.one/DataScienceT