How to read image file from S3 bucket directly into memory?

I have the following code

import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np
import boto3
s3 = boto3.resource('s3', region_name='us-east-2')
bucket = s3.Bucket('sentinel-s2-l1c')
object = bucket.Object('tiles/10/S/DG/2015/12/7/0/B01.jp2')
object.download_file('B01.jp2')
img=mpimg.imread('B01.jp2')
imgplot = plt.imshow(img)
plt.show(imgplot)

and it works. But the problem it downloads file into current directory first. Is it possible to read file and decode it as image directly in RAM?

Solution 1:

I would suggest using io module to read the file directly in to memory, without having to use a temporary file at all.

For example:

import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np
import boto3
import io

s3 = boto3.resource('s3', region_name='us-east-2')
bucket = s3.Bucket('sentinel-s2-l1c')
object = bucket.Object('tiles/10/S/DG/2015/12/7/0/B01.jp2')

file_stream = io.StringIO()
object.download_fileobj(file_stream)
img = mpimg.imread(file_stream)
# whatever you need to do

You could also use io.BytesIO if your data is binary.

Solution 2:

Further development from Greg Merritt's answer to solve all errors in the comment section, using BytesIO instead of StringIO, using PIL Image instead of matplotlib.image.

The following function works for python3 and boto3. Similarly, write_image_to_s3 function is a bonus.

from PIL import Image
from io import BytesIO
import numpy as np

def read_image_from_s3(bucket, key, region_name='ap-southeast-1'):
    """Load image file from s3.

    Parameters
    ----------
    bucket: string
        Bucket name
    key : string
        Path in s3

    Returns
    -------
    np array
        Image array
    """
    s3 = boto3.resource('s3', region_name='ap-southeast-1')
    bucket = s3.Bucket(bucket)
    object = bucket.Object(key)
    response = object.get()
    file_stream = response['Body']
    im = Image.open(file_stream)
    return np.array(im)

def write_image_to_s3(img_array, bucket, key, region_name='ap-southeast-1'):
    """Write an image array into S3 bucket

    Parameters
    ----------
    bucket: string
        Bucket name
    key : string
        Path in s3

    Returns
    -------
    None
    """
    s3 = boto3.resource('s3', region_name)
    bucket = s3.Bucket(bucket)
    object = bucket.Object(key)
    file_stream = BytesIO()
    im = Image.fromarray(img_array)
    im.save(file_stream, format='jpeg')
    object.put(Body=file_stream.getvalue())

Solution 3:

Greg Merritt's answer below is better method.

I'd like to suggest using Python's NamedTemporaryFile in tempfile module. It creates temporary files that will be deleted as file is closed (Thanks to @NoamG)

import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np
import boto3
import tempfile

s3 = boto3.resource('s3', region_name='us-east-2')
bucket = s3.Bucket('sentinel-s2-l1c')
object = bucket.Object('tiles/10/S/DG/2015/12/7/0/B01.jp2')
tmp = tempfile.NamedTemporaryFile()

with open(tmp.name, 'wb') as f:
    object.download_fileobj(f)
    img=mpimg.imread(tmp.name)
    # ...Do jobs using img

Solution 4:

Streaming the image is possible by specifying the file format in imread().

import boto3
from io import BytesIO
import matplotlib.image as mpimg
import matplotlib.pyplot as plt

resource = boto3.resource('s3', region_name='us-east-2')
bucket = resource.Bucket('sentinel-s2-l1c')

image_object = bucket.Object('tiles/10/S/DG/2015/12/7/0/B01.jp2')
image = mpimg.imread(BytesIO(image_object.get()['Body'].read()), 'jp2')

plt.figure(0)
plt.imshow(image)

Solution 5:

Slightly different approach using client:

import boto3
import io
from matplotlib import pyplot as plt

client = boto3.client("s3")

bucket='my_bucket'
key= 'my_key'

outfile = io.BytesIO()
client.download_fileobj(bucket, key, outfile)
outfile.seek(0)
img = plt.imread(outfile)

plt.imshow(img)
plt.show()