Here is the code:
from os import listdir
from os.path import isfile, join
vvy_imgs = []
#images to tensors
for img in np.array([f for f in listdir('E:/vachan') if isfile(join('E:/vachan', f))]): # filepaths
print(img) # shows it's of jpg extension
tensor = tf.io.decode_jpeg(img, channels=3)
vvy_imgs = np.append(vvy_imgs, tensor)
#Data Augmentation
for img in vvy_imgs:
tf.image.flip_left_right(img)
vvy_imgs = np.append(vvy_imgs, img)
but it is showing error
InvalidArgumentError: Unknown image file format. One of JPEG, PNG, GIF, BMP required. [Op:DecodeJpeg]
though all the images are of '.jpg' extension.
CodePudding user response:
Seems like img
is a path to an image and not an image.
Maybe try:
image = tf.io.read_file(img)
tensor= tf.io.decode_jpeg(image)
...