# Error with music\_inference\_model **URL:** \ **Category:** Sequence Models\ **Tags:** coursera-platform\ **Created:** [June 29, 2021, 7:02pm UTC](https://community.deeplearning.ai/t/error-with-music-inference-model/18097 "2021-06-29T19:02:11Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![HarshShah03](https://avatars.discourse-cdn.com/v4/letter/h/e0b2c6/32.png) [@HarshShah03](https://community.deeplearning.ai/u/HarshShah03)\ **Post date:** [June 29, 2021, 7:02pm UTC](https://community.deeplearning.ai/t/error-with-music-inference-model/18097/1 "2021-06-29T19:02:11Z")
The error that keeps coming up is: AttributeError: The layer “lstm” has multiple inbound nodes, with different output shapes. Hence the notion of “output shape” is ill-defined for the layer. Use `get_output_shape_at(node_index)` instead. My code for music\_inference\_model is: _{mentor edit: code removed - not allowed by the course Honor Code}_ The error comes up while trying to run : #UNIT TEST inference\_summary = summary(inference\_model) comparator(inference\_summary, music\_inference\_model\_out) Any kind of help is highly appreciated, thanks! ---
**Author:** ![Kic](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/kic/32/76339_2.png) [@Kic](https://community.deeplearning.ai/u/Kic)\ **Post date:** [June 29, 2021, 8:46pm UTC](https://community.deeplearning.ai/t/error-with-music-inference-model/18097/2 "2021-06-29T20:46:48Z")
Hi @HarshShah03 , You coded incorrectly in two places: 1. tf.math.argmax(), the parameter axis shouldn’t be set to -1 Please refer to this [link](https://www.tensorflow.org/api_docs/python/tf/math/argmax) from the official doc for details. 2. n\_values should not be used as depth for the call of tf.one\_hot(). x has the dimension of n\_values, so the depth should just be 1. Please be reminded of the honour code policy and do not post your code publicly.