I am receiving the following error when attempting to fit my model for training: Can not squeeze dim, expected a dimension of 1, got 9 [Op:Squeeze]
The model runs on a singular sample batch but throws the error when I try to fit the entire dataset
batch_size = 64 vocab_size = 42 embedding_dim = 256 rnn_units = 1024 steps_per_epoch = examples_per_epoch//BATCH_SIZE model = tf.keras.Sequential([ tf.keras.layers.Flatten(input_shape=(64,900),batch_input_shape=[batch_size, None]), tf.keras.layers.Embedding(vocab_size, embedding_dim, batch_input_shape=[batch_size, None]), rnn(rnn_units, return_sequences=True, recurrent_initializer='glorot_uniform', stateful=True), tf.keras.layers.Dense(vocab_size), ]) model.compile( optimizer = tf.train.AdamOptimizer(), loss = tf.losses.sparse_softmax_cross_entropy) model.fit(dataset.repeat(), epochs=EPOCHS, steps_per_epoch=steps_per_epoch, callbacks=[checkpoint_callback])
each batch input had the following shape (64,100,9) I suspect the issue is somewhere in and around where I have flattened this.
Any suggestions would be greatly appreciated, thanks