# Getting Started - Neural Network Inference

**URL:** <https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708>\
**Category:** d2l\
**Created:** [November 12, 2019, 12:17am UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708 "2019-11-12T00:17:15Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![mli](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/mli/32/1014_2.png) [@mli](https://discuss.tvm.apache.org/u/mli)\
**Post date:** [November 12, 2019, 12:17am UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708/1 "2019-11-12T00:17:15Z")

</div>

A placeholder for the book, discussion threads are embedded into the following page:

[http://tvm.d2l.ai/chapter\_getting\_started/from\_mxnet.html](http://tvm.d2l.ai/chapter_getting_started/from_mxnet.html)

---

<div class="post-metadata">

**Author:** ![comaniac](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/comaniac/32/899_2.png) [@comaniac](https://discuss.tvm.apache.org/u/comaniac)\
**Post date:** [November 12, 2019, 8:05pm UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708/2 "2019-11-12T20:05:51Z")

</div>

I consider the readers will confuse about Relay as we never mentioned it before in this book. Should we have a chapter to explain what is Relay and how it works with TVM?

---

<div class="post-metadata">

**Author:** ![mli](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/mli/32/1014_2.png) [@mli](https://discuss.tvm.apache.org/u/mli)\
**Post date:** [November 12, 2019, 9:28pm UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708/3 "2019-11-12T21:28:25Z")

</div>

Agree, plan to have a section late (in the neural network chapter) to explain it in details. Also it’s a good idea to explain a little bit more about relay in this section.

---

<div class="post-metadata">

**Author:** ![tiandiao123](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/tiandiao123/32/1891_2.png) [@tiandiao123](https://discuss.tvm.apache.org/u/tiandiao123)\
**Post date:** [June 8, 2020, 12:25am UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708/4 "2020-06-08T00:25:38Z")

</div>

Thanks for this tutorial!

---

<div class="post-metadata">

**Author:** ![Toma62299781](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/toma62299781/32/1992_2.png) [@Toma62299781](https://discuss.tvm.apache.org/u/Toma62299781)\
**Post date:** [September 19, 2020, 5:05am UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708/6 "2020-09-19T05:05:55Z")

</div>

Thanks for your comprehensive tutorial! However, there might be a minor typo in the end of chapter 1.3.5. As you can see, the code exactly above section 1.3.6 which is `tvm.testing.assert_allclose(loaded_scores, scores)` should be `np.testing.assert_allclose(loaded_scores, scores)` .

---

<div class="post-metadata">

**Author:** ![woojinnn](https://discuss.tvm.apache.org/letter_avatar_proxy/v4/letter/w/9dc877/32.png) [@woojinnn](https://discuss.tvm.apache.org/u/woojinnn)\
**Post date:** [October 26, 2020, 6:20am UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708/7 "2020-10-26T06:20:10Z")

</div>

Thanks for this tutorial! I want to recommend 2 additional stuffs that I got suffered while reading this tutorial.

1. Simple instruction about where to download ImageNet 1k dataset.
2. Additional comments about image\_processing function.

Thank you.

---

<div class="post-metadata">

**Author:** ![lookup1980](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/lookup1980/32/3094_2.png) [@lookup1980](https://discuss.tvm.apache.org/u/lookup1980)\
**Post date:** [September 20, 2021, 9:03pm UTC](https://discuss.tvm.apache.org/t/getting-started-neural-network-inference/4708/8 "2021-09-20T21:03:19Z")

</div>

Thanks for the tutorial! But it’s better to have command to download related files: …/data/imagenet1k\_labels.txt …/data/cat.jpg