CODEWITHSUNDEEP
pythonpython-2.7image-processingtensorflowtensor
whoisraibolt
whoisraibolt

Reputation: 2698

Save tensor as JPEG image with tf.map_fn - Python/TensorFlow

I have a function that returns me a variable called layer - images in the format:

<tf.Tensor 'Conv2D_1:0' shape=(?, 16, 16, 1) dtype=float32>

I need to save these images in .jpeg.

So far I've thought of doing this:

# Reshape into tf.image.encode_jpeg format
images = tf.image.convert_image_dtype(layer, tf.uint8)

train_batch_size = 300

And in session = tf.Session ()

images_encode = tf.map_fn(lambda x: tf.image.encode_jpeg(x), images, dtype=tf.uint8) # There was no error in this line, is it right?

My doubt now is how to configure it to save them?

I've tried this:

# That means it will only scroll through my 300 images
# And it's these 300 images that I want to save
x_batch, y_true_batch = next_batch_size(train_batch_size)

feed_dict_train = {x: x_batch, y_true: y_true_batch}

result = session.run(images_encode, feed_dict=feed_dict_train)

format_str = ('%s.jpeg')
fr = format_str % datetime.now()
f = open(fr, "wb+")
f.write(result.eval())
f.close()

But I'm getting the following error:

InvalidArgumentError (see above for traceback): TensorArray dtype is uint8 but Op is trying to write dtype string.
    [[Node: map_5/while/TensorArrayWrite/TensorArrayWriteV3 = TensorArrayWriteV3[T=DT_STRING, _class=["loc:@map_5/TensorArray_1"], _device="/job:localhost/replica:0/task:0/cpu:0"](map_5/while/TensorArrayWrite/TensorArrayWriteV3/Enter, map_5/while/Identity, map_5/while/EncodeJpeg, map_5/while/Identity_1)]]

My placeholders are:

# Placeholder variable for the input images
x = tf.placeholder(tf.float32, shape=[None, img_size_flat], name='x')

# Reshape 'x'
x_image = tf.reshape(x, [-1, img_size, img_size, num_channels])

# Placeholder variable for the true labels associated with the images
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')

Upvotes: 0

Views: 1619

Answers (1)

Patwie
Patwie

Reputation: 4450

Your are almost done. The type needs to be a tf.string: This gives a noisy image:

import tensorflow as tf
import numpy as np

noise = np.random.randn(3, 128, 128, 1).astype(np.float32) * 255
# your data
layer = tf.convert_to_tensor(noise)

images = tf.image.convert_image_dtype(layer, tf.uint8)
images_encode = tf.map_fn(lambda x: tf.image.encode_jpeg(x),
                          images, dtype=tf.string)


def write_jpg(buf, fn):
    with open(fn, 'wb') as f:
        f.write(encoded_jpegs[0])

with tf.Session() as sess:
    encoded_jpegs = sess.run(images_encode)

    for k, jpg in enumerate(encoded_jpegs):
        with open("test%03i.jpg" % k, 'wb') as f:
            f.write(jpg)

Upvotes: 1

Related Questions