Failed to find data adapter that can handle input: <class 'int'>, <class 'numpy.ndarray'>

[kelixirr]

Facing this issue with the latest version of Tensorflow. Classification Problem: Video: 96

Here is my code:

tf.random.set_seed(42)

model_13 = tf.keras.Sequential([
  tf.keras.layers.Flatten(input_shape=(28,28)),
  tf.keras.layers.Dense(4, activation='relu'),                              
  tf.keras.layers.Dense(4, activation='relu'),                              
  tf.keras.layers.Dense(10, activation='softmax')                              
])

model_13.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(),
                 optimizer=tf.keras.optimizers.Adam(),
                 metrics=['accuracy'])

norm_history = model_13.fit(tf.expand_dims(train_data_norm, axis=-1), train_labels, epochs=10,
                            validation_data=(test_data_norm, test_labels))`

Error

Epoch 1/10
1857/1875 [============================>.] - ETA: 0s - loss: 1.0380 - accuracy: 0.6465
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
[<ipython-input-17-652a679a1f23>](https://localhost:8080/#) in <module>()
     13 
     14 norm_history = model_13.fit(tf.expand_dims(train_data_norm, axis=-1), train_labels, epochs=10,
---> 15                             validation_data=(test_data_norm, test_labels))

1 frames
[/usr/local/lib/python3.7/dist-packages/keras/engine/data_adapter.py](https://localhost:8080/#) in select_data_adapter(x, y)
    985         "Failed to find data adapter that can handle "
    986         "input: {}, {}".format(
--> 987             _type_name(x), _type_name(y)))
    988   elif len(adapter_cls) > 1:
    989     raise RuntimeError(

**ValueError:** **_Failed to find data adapter that can handle input: <class 'int'>, <class 'numpy.ndarray'>_**

[mrdbourke]

Hey @kelixirr,

What have you tried so far?

Your code looks a little different to the notebook so it's hard to tell what's going on.

Have you see the cell with model_13 in this notebook? https://github.com/mrdbourke/tensorflow-deep-learning/blob/main/02_neural_network_classification_in_tensorflow.ipynb

[kelixirr]

Hi, thanks for your reply. I rechecked it and this issue appears when I include the validation set while fitting the model. It's this line of code:
validation_data=(test_data_norm, test_labels). The model is working properly without it. Do you think there should be some kind of shape manipulation on test_data_norm? I followed through video and the codes are same.

[mrdbourke]

Yes that's likely where the error is coming from.

The code from the notebook is for model_13 is slightly different to yours:

### Code from notebook 02 for model_13

# Set random seed
tf.random.set_seed(42)

# Create the model
model_13 = tf.keras.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)), # input layer (we had to reshape 28x28 to 784)
  tf.keras.layers.Dense(4, activation="relu"),
  tf.keras.layers.Dense(4, activation="relu"),
  tf.keras.layers.Dense(10, activation="softmax") # output shape is 10, activation is softmax
])

# Compile the model
model_13.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(),
                 optimizer=tf.keras.optimizers.Adam(),
                 metrics=["accuracy"])

# Create the learning rate callback
lr_scheduler = tf.keras.callbacks.LearningRateScheduler(lambda epoch: 1e-3 * 10**(epoch/20))

# Fit the model
find_lr_history = model_13.fit(train_data,
                               train_labels,
                               epochs=40, # model already doing pretty good with current LR, probably don't need 100 epochs
                               validation_data=(test_data, test_labels),
                               callbacks=[lr_scheduler])

If you run code with different formatted datasets (e.g. test_data_norm vs test_data) you'll likely get different results/warnings.