# Train Model with multiple features

**URL:** <https://discuss.ai.google.dev/t/train-model-with-multiple-features/32137>\
**Category:** General Discussion\
**Tags:** keras-model, lstm\
**Created:** [January 4, 2024, 7:08am UTC](https://discuss.ai.google.dev/t/train-model-with-multiple-features/32137 "2024-01-04T07:08:06Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Bharadwaj\_D](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/bharadwaj_d/32/17588_2.png) [@Bharadwaj\_D](https://discuss.ai.google.dev/u/Bharadwaj_D)\
**Post date:** [January 4, 2024, 7:08am UTC](https://discuss.ai.google.dev/t/train-model-with-multiple-features/32137/1 "2024-01-04T07:08:07Z")

</div>

I’m trying to train LSTM model with multiple feature inputs and 1 output.  
I get the following error  
non-broadcastable output operand with shape (90,1) doesn’t match the broadcast shape (90,2)

```auto
model = Sequential()
    model.add(LSTM(units=50, return_sequences=True, input_shape=(sequence_length, num_features)))
    model.add(LSTM(units=50))
    model.add(Dense(units=1))
    model.compile(optimizer='adam', loss='mse')
    return model

```

How can i resolve this error.

---

<div class="post-metadata">

**Author:** ![Kiran\_Sai\_Ramineni](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/kiran_sai_ramineni/32/8859_2.png) [@Kiran\_Sai\_Ramineni](https://discuss.ai.google.dev/u/Kiran_Sai_Ramineni)\
**Post date:** [January 5, 2024, 6:41am UTC](https://discuss.ai.google.dev/t/train-model-with-multiple-features/32137/3 "2024-01-05T06:41:32Z")

</div>

Hi @Bharadwaj_D, Could you please make sure that final dense layer units are equal to the number of features in your y\_train. For example if your y\_train has a shape (100,5) then the dense layer units should be 5 . The model expects the final dense layer units to be equal to the number of output features. Thank You.

---

<div class="post-metadata">

**Author:** ![Bharadwaj\_D](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/bharadwaj_d/32/17588_2.png) [@Bharadwaj\_D](https://discuss.ai.google.dev/u/Bharadwaj_D)\
**Post date:** [January 8, 2024, 6:27am UTC](https://discuss.ai.google.dev/t/train-model-with-multiple-features/32137/5 "2024-01-08T06:27:14Z")

</div>

Where can i learn more about LSTM models for free

---

<div class="post-metadata">

**Author:** ![Kiran\_Sai\_Ramineni](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/kiran_sai_ramineni/32/8859_2.png) [@Kiran\_Sai\_Ramineni](https://discuss.ai.google.dev/u/Kiran_Sai_Ramineni)\
**Post date:** [January 11, 2024, 6:40am UTC](https://discuss.ai.google.dev/t/train-model-with-multiple-features/32137/7 "2024-01-11T06:40:28Z")

</div>

Hi @Bharadwaj_D, You can refer to articles available online. like medium [articles](https://towardsdatascience.com/lstm-by-example-using-tensorflow-feb0c1968537) etc. Thank You.