Train the model error - cat vs dog

Course Q&A TensorFlow Developer Professional Convolutional Neural Networks in TensorFlow
1 
Found 22498 images belonging to 2 classes.Found 2500 images belonging to 2 classes.
``` after successfully train and validate cat and dog images in the last it show me this 2 error but 1 are UnknownError  history = model.fit(train_generator, epochs=15,  verbose=1, 
and 2 is UnknownError: Graph execution error:

2 root error(s) found.
  (0) UNKNOWN:  UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7f03a05320e0>
Traceback
2

See this please.

1 Like
4

Sir it still show me this error when I try to run train model

5

666.jpg is zero length, so ignoring.
11702.jpg is zero length, so ignoring
This aren’t see sir it only see:-
original cat’s directory has 12500 images
Original dog’s directory has 12500 images

There are 11249 Images of cats for training
There are 11249 Images of dog for training
There are 1250 Images of cats for validation
There are 1250 Images of dog for validation

6

If you are using valid image paths, please click my name and message your notebook as an attachment.

7

@Parshva_Shah

Please don’t use os.path.isfile to filter invalid images. As recommended in the assignment markdown, use os.path.getsize to confirm if a file is empty which would make it an invalid image.