Error while working with FoodVision

[reshma93s]

I am getting an error where the data is batched and pre-processed.

Map preprocessing function to training data (and paralellize)

train_data = train_data.map(map_func=preprocess_img, num_parallel_calls=tf.data.AUTOTUNE)

Shuffle train_data and turn it into batches and prefetch it (load it faster)

train_data = train_data.shuffle(buffer_size=1000).batch(batch_size=32).prefetch(buffer_size=tf.data.AUTOTUNE)

Error:-

---

ValueError Traceback (most recent call last)
in ()
1 # Map preprocessing function to training data (and paralellize)
----> 2 train_data = train_data.map(map_func=preprocess_img, num_parallel_calls=tf.data.AUTOTUNE)
3 # Shuffle train_data and turn it into batches and prefetch it (load it faster)
4 train_data = train_data.shuffle(buffer_size=1000).batch(batch_size=32).prefetch(buffer_size=tf.data.AUTOTUNE)

10 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/autograph/impl/api.py in wrapper(*args, **kwargs)
690 except Exception as e: # pylint:disable=broad-except
691 if hasattr(e, 'ag_error_metadata'):
--> 692 raise e.ag_error_metadata.to_exception(e)
693 else:
694 raise

ValueError: in user code:

File "<ipython-input-20-16eda5b2fbee>", line 6, in preprocess_img  *
    image = tf.image.resize(image,[img_shape,img_shape])

ValueError: 'images' must have either 3 or 4 dimensions.

[AIWithShrey]

Hello, Make sure you include the color channels in your shape. It is 3 (for RGB) if the images are colored or 1 if the images are in greyscale.

On Tue, Jul 19, 2022 at 4:09 PM reshma93s ***@***.***> wrote: I am getting an error where the data is batched and pre-processed. Map preprocessing function to training data (and paralellize) train_data = train_data.map(map_func=preprocess_img, num_parallel_calls=tf.data.AUTOTUNE) Shuffle train_data and turn it into batches and prefetch it (load it faster) train_data = train_data.shuffle(buffer_size=1000).batch(batch_size=32).prefetch(buffer_size=tf.data.AUTOTUNE) Error:- ------------------------------ ValueError Traceback (most recent call last) <https://localhost:8080/#> in () 1 # Map preprocessing function to training data (and paralellize) ----> 2 train_data = train_data.map(map_func=preprocess_img, num_parallel_calls=tf.data.AUTOTUNE) 3 # Shuffle train_data and turn it into batches and prefetch it (load it faster) 4 train_data = train_data.shuffle(buffer_size=1000).batch(batch_size=32).prefetch(buffer_size=tf.data.AUTOTUNE) 10 frames /usr/local/lib/python3.7/dist-packages/tensorflow/python/autograph/impl/api.py <https://localhost:8080/#> in wrapper(*args, **kwargs) 690 except Exception as e: # pylint:disable=broad-except 691 if hasattr(e, 'ag_error_metadata'): --> 692 raise e.ag_error_metadata.to_exception(e) 693 else: 694 raise ValueError: in user code: File "<ipython-input-20-16eda5b2fbee>", line 6, in preprocess_img * image = tf.image.resize(image,[img_shape,img_shape]) ValueError: 'images' must have either 3 or 4 dimensions. — Reply to this email directly, view it on GitHub <#414>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AF2IW5WT6YJQZ2IHYDSPRG3VU2AU3ANCNFSM537PNPNA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

-- Warmest Regards, Shreyas Mocherla Student of Grade 12, Indus International School Hyderabad Visit my page at shreyasm.com

[Jinay777]

i am also getting the same error
@reshma93s Got Any Solution

[mrdbourke]

Hey @Jinay777 ,

Have you tried checking the sizes of your images?

Potentially have you tried checking to see if the function works on one image and then trying to resize multiple images at a time?