Input to reshape is a tensor with 'batch_size' values, but the requested shape requires a multiple of 'n_features' - python-3.x

Question

I'm trying to make own attention model and I found example code in here:
https://www.kaggle.com/takuok/bidirectional-lstm-and-attention-lb-0-043
and it works just fine when I run it without modification.
But my own data contain only numeric values, I had to change example code.
so I erase embedding part in example code and plus, this is what I fixed.
xtr = np.reshape(xtr, (xtr.shape[0], 1, xtr.shape[1]))
# xtr.shape() = (n_sample_train, 1, 150), y.shape() = (n_sample_train, 6)
xte = np.reshape(xte, (xte.shape[0], 1, xte.shape[1]))
# xtr.shape() = (n_sample_test, 1, 150)
model = BidLstm(maxlen, max_features)
model.compile(loss='binary_crossentropy', optimizer='adam',
metrics=['accuracy'])
and my BidLstm func looks like,
def BidLstm(maxlen, max_features):
inp = Input(shape=(1,150))
#x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp) -> I don't need embedding since my own data is numeric.
x = Bidirectional(LSTM(300, return_sequences=True, dropout=0.25,
recurrent_dropout=0.25))(inp)
x = Attention(maxlen)(x)
x = Dense(256, activation="relu")(x)
x = Dropout(0.25)(x)
x = Dense(6, activation="sigmoid")(x)
model = Model(inputs=inp, outputs=x)
return model
and it said,
InvalidArgumentErrorTraceback (most recent call last)
<ipython-input-62-929955370368> in <module>
29
30 early = EarlyStopping(monitor="val_loss", mode="min", patience=1)
---> 31 model.fit(xtr, y, batch_size=128, epochs=15, validation_split=0.1, callbacks=[early])
32 #model.fit(xtr, y, batch_size=256, epochs=1, validation_split=0.1)
33
/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
1037 initial_epoch=initial_epoch,
1038 steps_per_epoch=steps_per_epoch,
-> 1039 validation_steps=validation_steps)
1040
1041 def evaluate(self, x=None, y=None,
/usr/local/lib/python3.5/dist-packages/keras/engine/training_arrays.py in fit_loop(model, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
197 ins_batch[i] = ins_batch[i].toarray()
198
--> 199 outs = f(ins_batch)
200 outs = to_list(outs)
201 for l, o in zip(out_labels, outs):
/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
2713 return self._legacy_call(inputs)
2714
-> 2715 return self._call(inputs)
2716 else:
2717 if py_any(is_tensor(x) for x in inputs):
/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py in _call(self, inputs)
2673 fetched = self._callable_fn(*array_vals, run_metadata=self.run_metadata)
2674 else:
-> 2675 fetched = self._callable_fn(*array_vals)
2676 return fetched[:len(self.outputs)]
2677
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)
1437 ret = tf_session.TF_SessionRunCallable(
1438 self._session._session, self._handle, args, status,
-> 1439 run_metadata_ptr)
1440 if run_metadata:
1441 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
526 None, None,
527 compat.as_text(c_api.TF_Message(self.status.status)),
--> 528 c_api.TF_GetCode(self.status.status))
529 # Delete the underlying status object from memory otherwise it stays alive
530 # as there is a reference to status from this from the traceback due to
InvalidArgumentError: Input to reshape is a tensor with 128 values, but the requested shape requires a multiple of 150
[[{{node attention_16/Reshape_2}}]]
[[{{node loss_5/mul}}]]
I think something wrong in loss function saids in here:
Input to reshape is a tensor with 2 * "batch_size" values, but the requested shape has "batch_size"
but I don't know which part to fix it.
my keras and tensorflow versions are 2.2.4 and 1.13.0-rc0
please help. thanks.
Edit 1
I've change my batch size, like keras saids, multiple of 150(batch_size = 150). than it reports
Train on 143613 samples, validate on 15958 samples
Epoch 1/15
143400/143613 [============================>.] - ETA: 0s - loss: 0.1505 - acc: 0.9619
InvalidArgumentError: Input to reshape is a tensor with 63 values, but the requested shape requires a multiple of 150
[[{{node attention_18/Reshape_2}}]]
[[{{node metrics_6/acc/Mean_1}}]]
and details is same as before. what should I do?

Answer 1

Your input shape must be (150,1).
LSTM shapes are (batch, steps, features). It's pointless to use LSTMs with 1 step only. (Unless you are using custom training loops with stateful=True, which is not your case).