# How train TF lite model using user input?

**URL:** <https://discuss.ai.google.dev/t/how-train-tf-lite-model-using-user-input/26445>\
**Category:** General Discussion\
**Tags:** tflite, model\
**Created:** [May 27, 2024, 5:37am UTC](https://discuss.ai.google.dev/t/how-train-tf-lite-model-using-user-input/26445 "2024-05-27T05:37:52Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Abhi\_1](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/abhi_1/32/17754_2.png) [@Abhi\_1](https://discuss.ai.google.dev/u/Abhi_1)\
**Post date:** [May 27, 2024, 5:37am UTC](https://discuss.ai.google.dev/t/how-train-tf-lite-model-using-user-input/26445/1 "2024-05-27T05:37:52Z")

</div>

i have tensorflow lite audio classification model i want to improve its accuracy by incorporating /feeding user input how can we achieve it using python programs ?  
I don’t want to retrain the model again.

---

<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:** [June 4, 2024, 11:23am UTC](https://discuss.ai.google.dev/t/how-train-tf-lite-model-using-user-input/26445/3 "2024-06-04T11:23:10Z")

</div>

Hi @Abhi, Once the model is trained with the defined input shape the model does not accept the other shapes. one thing you can do is reshape the user input data to the model input shape and can pass the data to the model. Thank You.

---

<div class="post-metadata">

**Author:** ![arnoldmatt](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/arnoldmatt/32/14505_2.png) [@arnoldmatt](https://discuss.ai.google.dev/u/arnoldmatt)\
**Post date:** [June 5, 2024, 11:16am UTC](https://discuss.ai.google.dev/t/how-train-tf-lite-model-using-user-input/26445/5 "2024-06-05T11:16:48Z")

</div>

You can’t directly retrain a TFLite model with user input, but Python lets you build an interactive loop for feedback and data collection for future retraining.