https://github.com/rakibhhridoy/imageprocessing

Large amount of image processing is quite messy and time consuming,thus the working steps should be fast as well as accurate also. I've made sequential functions that is needed for processing data in TensorFlow and python. These functions made my work fast as it needed in commercial purposes.
https://github.com/rakibhhridoy/imageprocessing

augmentation deep-learning functional-programming image-manipulation image-processing keras machine-learning numpy python sequential-patterns tensorflow

Last synced: about 1 month ago
JSON representation

Large amount of image processing is quite messy and time consuming,thus the working steps should be fast as well as accurate also. I've made sequential functions that is needed for processing data in TensorFlow and python. These functions made my work fast as it needed in commercial purposes.

• Host: GitHub
• URL: https://github.com/rakibhhridoy/imageprocessing
• Owner: rakibhhridoy
• Created: 2020-06-26T12:00:59.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2021-05-19T00:04:09.000Z (over 3 years ago)
• Last Synced: 2024-11-06T15:27:07.881Z (3 months ago)
• Topics: augmentation, deep-learning, functional-programming, image-manipulation, image-processing, keras, machine-learning, numpy, python, sequential-patterns, tensorflow
• Language: Python
• Homepage: https://rakibhhridoy.github.io
• Size: 112 KB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

        
# *Image Processing For Deep learning-FunctionedWay*

>Before Using these functions you have to make sure your directory pattern look like below:

![img1](i0.png)

### *Function Available*

>unzipping_file  


>joining_directory_to_each_other_binary_class 


>training_filename_show 


>train_validation_size 


>plotting_image 


>resize_labeled_images 


>resize_labeled_images_augmentation 


>training_with_loading 


>load_fit_again_saved_model 


>evaluate_the_model_performance 


>images_in_conv_layer 


>upload_image_to_test 


>test_image 


>clean_up 


1. We will join the directory and thus it will save us huge amount of time. 

```python

from Updated import imagePyTen

import os

import zipfile

import matplotlib.image as mpimg

import matplotlib.pyplot as plt

from tensorflow.keras.preprocessing.image import ImageDataGenerator

import random

from tensorflow.keras.preprocessing.image import img_to_array, load_img

from google.colab import files

import matplotlib.pyplot as plt

from keras.preprocessing import image

```

2. Use as your need.

   

### Get Touch With Me:

[Linkedin](https://linkedin.com/in/rakibhhridoy) 


[RakibHHridoy](https://rakibhhridoy.github.io)