python - Data cardinality is ambiguous: Make sure all arrays contain the same number of samples

Question

I'm passing a numpy array of dtype float32 as my model's x, and a numpy array of dtype float32 as my model's y. Both arrays have the same number of elements:

print(f"truth shape: {train_truth_sample_array[0].shape}, count: {len(train_truth_sample_array)}") 
# truth shape: (80000,), count: 100


print(f"downscaled shape: {train_downscaled_sample_array[0].shape}, count: {len(train_downscaled_sample_array)}") 
# downscaled shape: (40000,), count: 100

model = Sequential([
                    Input(shape=train_downscaled_sample_array[0].shape),
                    Dense(units=1000),
])

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())

EPOCHS = 100
history = model.fit(x=train_downscaled_sample_array,
                    y=train_truth_sample_array,
                    epochs=EPOCHS,
                    callbacks=tf.keras.callbacks.EarlyStopping(verbose=1, patience=2))

But I'm getting the following error:

Data cardinality is ambiguous:
  x sizes: 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000, 40000
  y sizes: 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000, 80000
Make sure all arrays contain the same number of samples.

Why is this? Both arrays have the same count of elements...

question from:https://stackoverflow.com/questions/66051207/data-cardinality-is-ambiguous-make-sure-all-arrays-contain-the-same-number-of-s

Answer 1

Waitting for answers