0

Here i want to save the augmented pictures to a directory.but that didn't happend using the below code.I am beginner .Please Help.Thanks in advance.

import tensorflow as tf
import matplotlib.pyplot as plt
import os
import cv2
import numpy as np
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.preprocessing import image

train_datagen = ImageDataGenerator(
    rescale=1./255,
    shear_range=0.2,
    validation_split=0.2,
    zoom_range=0.2,
    horizontal_flip=True,
    brightness_range=[0.2,1.0],
    )

    
train_generator = train_datagen.flow_from_directory(
    r'C:\Users\Mahmudul Hasan\Desktop\practice',
    target_size=(150, 150),
    batch_size=32,
    class_mode='categorical',
    seed=42,
    subset="training",
    save_to_dir=r"C:\Users\Mahmudul Hasan\Desktop\Augmented data" )
Mahmudul Hasan Munna
  • 11
  • 2

1 Answers1

0

train_datagen.flow_from_directory gives you a generator. To really generate the image, use this example code:

i = 0
for batch in train_datagen.flow_from_directory(input_dir, target_size=(150, 150),
class_mode='binary', shuffle=False, 
save_to_dir=output_dir, save_prefix='aug'):
i += 1
if i > 20: 
    break
Jeremy Caney
  • 7,102
  • 69
  • 48
  • 77
minhhk
  • 1
  • 1