manzke

https://medium.com/@danielmanzke/how-i-used-chatgpt-to-exploit-another-tool-which-uses-chatgpt-b0885a89b210

manzke

# script to create movie from multiple png files
# taken in choronoligcal order

# start at 0
count=0
# take all files named shot - something ordered by date
for f in `ls fakes*.jpg`
do 
  # get the index in 0000 format
  printf -v counts "%06d" $count

manzke

manzke

manzke

manzke

Example usage of MODNet (https://github.com/ZHKKKe/MODNet) for Background Removal in CPU Mode. I've adopted their interference code.

PR ZHKKKe/MODNet#161

Get weights gdown --id 1mcr7ALciuAsHCpLnrtG_eop5-EYhbCmz -O pretrained/modnet_photographic_portrait_matting.ckpt

They also have a nice Jupyterr Notebook https://colab.research.google.com/drive/1GANpbKT06aEFiW-Ssx0DQnnEADcXwQG6?usp=sharing#scrollTo=gEwiokUgkSDO

manzke

import logging
import matplotlib.pyplot as plt
import numpy as np
import os
import tensorflow as tf
import tensorflow_datasets as tfds
tf.keras.backend.clear_session()
from tensorflow.keras.layers import Conv2D, Conv2DTranspose, \
    Dense, Layer, Reshape, InputLayer, Flatten
from tqdm import tqdm

manzke

import os
import logging
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import tensorflow_datasets as tfds
tf.keras.backend.clear_session()
from tensorflow.keras.layers import Conv2D, Conv2DTranspose, \
    Dense, Layer, Reshape, InputLayer, Flatten
from tensorflow import keras

manzke

# import the necessary packages
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Model
from tensorflow.keras.applications.efficientnet import EfficientNetB3, EfficientNetB4, EfficientNetB5, preprocess_input

'''
    EfficientNetB0 - (224, 224, 3)
    EfficientNetB1 - (240, 240, 3)

manzke

Verifying my Blockstack ID is secured with the address 1NiVduDatTrtM5eCSAym5cbd5vhE71H8P3 https://explorer.blockstack.org/address/1NiVduDatTrtM5eCSAym5cbd5vhE71H8P3