I tried the style transfer from https://www.tensorflow.org/hub/tutorials/tf2_arbitrary_image_stylization on Google colab and i would like to read a local path from Google colab like '/content/a.jpg' instead of a url from other website what should i modify the code?
Try this
from google.colab import drive
drive.mount('/content/drive')
You can use your Google drive directory as an external drive.
Then lets say there is a file called a.jpg in your google drive main folder, you can point to it like this,
data_dir = '/content/drive/MyDrive/a.jpg'
if it is in a picture directory withing your drive, you can try this
data_dir = '/content/drive/MyDrive/pictures/a.jpg'
Then change the load_image function, to this,
@functools.lru_cache(maxsize=None)
def load_image(image_path, image_size=(256, 256), preserve_aspect_ratio=True):
"""Loads and preprocesses images."""
# Load and convert to float32 numpy array, add batch dimension, and normalize to range [0, 1].
img = tf.io.decode_image(
tf.io.read_file(image_path),
channels=3, dtype=tf.float32)[tf.newaxis, ...]
img = crop_center(img)
img = tf.image.resize(img, image_size, preserve_aspect_ratio=True)
return img
Then you can try,
load_image(data_dir)