# Input to reshape is a tensor with 102400 values, but the requested shape requires a multiple of 165888

**URL:** <https://community.deeplearning.ai/t/input-to-reshape-is-a-tensor-with-102400-values-but-the-requested-shape-requires-a-multiple-of-165888/150367>\
**Category:** Convolutional Neural Networks in TensorFlow\
**Tags:** week-module-4\
**Created:** [June 29, 2022, 8:41pm UTC](https://community.deeplearning.ai/t/input-to-reshape-is-a-tensor-with-102400-values-but-the-requested-shape-requires-a-multiple-of-165888/150367 "2022-06-29T20:41:04Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Pablo\_Gonzalez\_Uzeta](https://avatars.discourse-cdn.com/v4/letter/p/d9b06d/32.png) [@Pablo\_Gonzalez\_Uzeta](https://community.deeplearning.ai/u/Pablo_Gonzalez_Uzeta)\
**Post date:** [June 29, 2022, 8:41pm UTC](https://community.deeplearning.ai/t/input-to-reshape-is-a-tensor-with-102400-values-but-the-requested-shape-requires-a-multiple-of-165888/150367/1 "2022-06-29T20:41:04Z")

</div>

Befor using sparse\_categorical\_crossentropy i used to be getting :

ValueError: Shapes (None, 1) and (None, 26) are incompatible

Afterwards i am getting :

Node: ‘sequential\_3/flatten\_3/Reshape’  
Input to reshape is a tensor with 102400 values, but the requested shape requires a multiple of 165888  
[[{{node sequential\_3/flatten\_3/Reshape}}]] [Op:\_\_inference\_train\_function\_2600]

Evrything seems right, any ideas ?

---

<div class="post-metadata">

**Author:** ![balaji.ambresh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/balaji.ambresh/32/128697_2.png) [@balaji.ambresh](https://community.deeplearning.ai/u/balaji.ambresh)\
**Post date:** [June 30, 2022, 6:36am UTC](https://community.deeplearning.ai/t/input-to-reshape-is-a-tensor-with-102400-values-but-the-requested-shape-requires-a-multiple-of-165888/150367/2 "2022-06-30T06:36:02Z")

</div>

The number of output neurons should not be 1 since this is a multi class classification problem. So, the 1st feedback: `ValueError: Shapes (None, 1) and (None, 26) are incompatible` is correct.

As far as the 2nd error is concerned, please confirm that the `input_shape` parameter is set correctly.

---

<div class="post-metadata">

**Author:** ![Pablo\_Gonzalez\_Uzeta](https://avatars.discourse-cdn.com/v4/letter/p/d9b06d/32.png) [@Pablo\_Gonzalez\_Uzeta](https://community.deeplearning.ai/u/Pablo_Gonzalez_Uzeta)\
**Post date:** [June 30, 2022, 5:53pm UTC](https://community.deeplearning.ai/t/input-to-reshape-is-a-tensor-with-102400-values-but-the-requested-shape-requires-a-multiple-of-165888/150367/3 "2022-06-30T17:53:18Z")

</div>

Thank you, you were right.
