sentiment_analysis_24.py

for e in range(10):
    accuracy = []
    for batch, (text, label) in enumerate(train_data.take(-1)):
        with tf.GradientTape() as tape:
            logits = model(text)
            label = tf.expand_dims(label, 1)
            loss = loss_func(label, logits)

ValueError Traceback (most recent call last)
in
3 for batch, (text, label) in enumerate(train_data.take(-1)):
4 with tf.GradientTape() as tape:
----> 5 logits = model(text)
6 label = tf.expand_dims(label, 1)
7 loss = loss_func(label, logits)
ValueError: Input 0 of layer bidirectional_1 is incompatible with the layer: expected ndim=3, found ndim=5. Full shape received: [1, 1, 1, 164, 64]
I have this error while running the code.Please Rectify..!!!