# Transposed Convolutions

**URL:** <https://discuss.pytorch.org/t/transposed-convolutions/211366>\
**Category:** audio\
**Created:** [October 10, 2024, 7:00am UTC](https://discuss.pytorch.org/t/transposed-convolutions/211366 "2024-10-10T07:00:07Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Inigo\_Parra](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/i/d78d45/32.png) [@Inigo\_Parra](https://discuss.pytorch.org/u/Inigo_Parra)\
**Post date:** [October 10, 2024, 7:00am UTC](https://discuss.pytorch.org/t/transposed-convolutions/211366/1 "2024-10-10T07:00:07Z")

</div>

Hi!

I am having a hard time understanding the ConvTranspose1D layer. I would really appreciate if someone could help me understand the transposed convolutions better (in detail if possible)

Thank you!

---

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [October 10, 2024, 9:18pm UTC](https://discuss.pytorch.org/t/transposed-convolutions/211366/2 "2024-10-10T21:18:52Z")

</div>

The [`conv_arithmetic` repository](https://github.com/vdumoulin/conv_arithmetic/tree/master?tab=readme-ov-file#transposed-convolution-animations) could help as it’s visualizing how the layers perform their computation. The linked paper also describes it in more detail.

---

<div class="post-metadata">

**Author:** ![Inigo\_Parra](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/i/d78d45/32.png) [@Inigo\_Parra](https://discuss.pytorch.org/u/Inigo_Parra)\
**Post date:** [October 12, 2024, 4:14am UTC](https://discuss.pytorch.org/t/transposed-convolutions/211366/3 "2024-10-12T04:14:23Z")

</div>

This is great! Thank you!