Convert Image Files to a CSV File

Converting images to csv file in python

From your question, I think you want to know about numpy.flatten(). You want to add

value = value.flatten()

right before your np.savetxt call. It will flatten the array to only one dimension and it should then print out as a single line.

The rest of your question is unclear bit it implies you have a directory full of jpeg images and you want a way to read through them all. So first, get a file list:

def createFileList(myDir, format='.jpg'):
fileList = []
print(myDir)
for root, dirs, files in os.walk(myDir, topdown=False):
    for name in files:
        if name.endswith(format):
            fullName = os.path.join(root, name)
            fileList.append(fullName)
return fileList

The surround your code with a for fileName in fileList:

Edited to add complete example
Note that I've used csv writer and changed your float64 to ints (which should be ok as pixel data is 0-255

from PIL import Image
import numpy as np
import sys
import os
import csv

#Useful function
def createFileList(myDir, format='.jpg'):
fileList = []
print(myDir)
for root, dirs, files in os.walk(myDir, topdown=False):
    for name in files:
        if name.endswith(format):
            fullName = os.path.join(root, name)
            fileList.append(fullName)
return fileList

# load the original image
myFileList = createFileList('path/to/directory/')

for file in myFileList:
    print(file)
    img_file = Image.open(file)
    # img_file.show()

    # get original image parameters...
    width, height = img_file.size
    format = img_file.format
    mode = img_file.mode

    # Make image Greyscale
    img_grey = img_file.convert('L')
    #img_grey.save('result.png')
    #img_grey.show()

    # Save Greyscale values
    value = np.asarray(img_grey.getdata(), dtype=np.int).reshape((img_grey.size[1], img_grey.size[0]))
    value = value.flatten()
    print(value)
    with open("img_pixels.csv", 'a') as f:
        writer = csv.writer(f)
        writer.writerow(value)

Convert folder of images with labels in CSV file into a tensorflow Dataset

Based on the answers:

• https://stackoverflow.com/a/72343548/
• https://stackoverflow.com/a/54752691/

I have DIY created the following. I am sure there is a simpler way, but this at least is something functional. I was hoping for more built-in support though:

import os.path
from typing import Dict, Tuple

import pandas as pd
import tensorflow as tf


def get_full_dataset(
    batch_size: int = 32, image_size: Tuple[int, int] = (256, 256)
) -> tf.data.Dataset:
    data = pd.read_csv(os.path.join(DATA_ABS_PATH, "images.csv"))
    images_path = os.path.join(DATA_ABS_PATH, "images")
    data["image"] = data["image"].map(lambda x: os.path.join(images_path, f"{x}.jpg"))
    filenames: tf.Tensor = tf.constant(data["image"], dtype=tf.string)
    data["label"] = data["label"].str.lower()
    class_name_to_label: Dict[str, int] = {
        label: i for i, label in enumerate(set(data["label"]))
    }
    labels: tf.Tensor = tf.constant(
        data["label"].map(class_name_to_label.__getitem__), dtype=tf.uint8
    )
    dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))

    def _parse_function(filename, label):
        jpg_image: tf.Tensor = tf.io.decode_jpeg(tf.io.read_file(filename))
        return tf.image.resize(jpg_image, size=image_size), label

    dataset = dataset.map(_parse_function)
    return dataset.batch(batch_size)

How to convert Image files to CSV with label

from scipy.misc import imread
import numpy as np
import pandas as pd
import os
import imageio
import glob
import pathlib
v = []
for i,files in enumerate(pathlib.Path('./Train').glob('*/**/*.png')):
    im = imread(files.as_posix())
    value = im.flatten()
    value = np.hstack((int(files.parent.name),value))
    v.append(value)
df = pd.DataFrame(v)
df = df.sample(frac=1)
df.to_csv('train.csv',header=False,index=False)

This is how I corrected my code.

How to load .png images with image names listed in a .csv file to R

Something like this should work. If you load the csv into a dataframe then, it's then straightforward to point the image_read towards the appropriate elements.

And the index (row number) is included in the output filename so that things are not overwritten each iteration.

library (magick)

file_list <- read.csv("your.csv",header = F)
names(file_list) <- c("A","B","C")

for (i in 1:nrow(file_list)){
pic_A <- image_read(file_list$A[i])
pic_B <- image_read(file_list$B[i])
pic_C <- image_read(file_list$C[i])

combined <- c(pic_A, pic_B, pic_C)
combined <- image_scale(combined, "300x300")
image_info(combined)
final <- image_append(image_scale(combined, "x120"))
print(final)
image_write(final, paste0("final_",i,".png")) #to save
}

---

Related Topics