# Conser-vision Practice Area

**URL:** https://community.drivendata.org/c/conser-vision/87.md

[Latest](https://community.drivendata.org/latest.md) · [Categories](https://community.drivendata.org/categories.md)

---

## [About the Conser-vision Practice Area category](https://community.drivendata.org/t/about-the-conser-vision-practice-area-category/7611)

<div class="topic-metadata">

**Author:** [@mike-dd](https://community.drivendata.org/u/mike-dd)\
**Replies:** 0

</div>

This category is for posts about the Conser-vision Practice Area: Image Classification competition. Please keep all posts here specific to the competition. To start a new thread, click the \[+ Create Topic\] button and ma…

---

## [Transfer learning: What is ResNet learning?](https://community.drivendata.org/t/transfer-learning-what-is-resnet-learning/7907)

<div class="topic-metadata">

**Author:** [@DavidEis](https://community.drivendata.org/u/DavidEis)\
**Replies:** 1\
**Last updated:** [February 13, 2024, 10:04am UTC](https://community.drivendata.org/t/transfer-learning-what-is-resnet-learning/7907 "2024-02-13T10:04:27Z")

</div>

Dear Conser-visionists, ML / Deep Learning newbee here :slight\_smile: I’ve tried several approaches but couldn’t get any improvements over the benchmark results. To better understand what’s going on, I used the great b…

---

## [Questions about tutorial code](https://community.drivendata.org/t/questions-about-tutorial-code/9092)

<div class="topic-metadata">

**Author:** [@vlucet](https://community.drivendata.org/u/vlucet)\
**Replies:** 0\
**Last updated:** [August 24, 2023, 5:44pm UTC](https://community.drivendata.org/t/questions-about-tutorial-code/9092 "2023-08-24T17:44:58Z")

</div>

Hi there, I really enjoyed the tutorial, it provided a very good starting point. I was wondering of anyone could enlighten me on some of the choices thatw ere made concerning adapting the resnet50 model for our dataset. …

---

## [Ensuring Sites are in Test or Train](https://community.drivendata.org/t/ensuring-sites-are-in-test-or-train/8457)

<div class="topic-metadata">

**Author:** [@rothm](https://community.drivendata.org/u/rothm)\
**Replies:** 1\
**Last updated:** [July 3, 2023, 8:37am UTC](https://community.drivendata.org/t/ensuring-sites-are-in-test-or-train/8457 "2023-07-03T08:37:38Z")

</div>

Hello! There’s a suggestion in the problem description to ensure sites appear either in the train or the eval set, but not both. Does anyone have slick ways of doing this while maintaining stratified and balanced datase…

---

## [Submission from Google.colab](https://community.drivendata.org/t/submission-from-google-colab/8022)

<div class="topic-metadata">

**Author:** [@Falcon777](https://community.drivendata.org/u/Falcon777)\
**Replies:** 2\
**Last updated:** [November 17, 2022, 10:57pm UTC](https://community.drivendata.org/t/submission-from-google-colab/8022 "2022-11-17T22:57:54Z")

</div>

Excuse me for the question, but I’m a beginner. How can I make a submission from Google.colab. Thank you very much

---

## [Pretrained models](https://community.drivendata.org/t/pretrained-models/7813)

<div class="topic-metadata">

**Author:** [@sumatorikki](https://community.drivendata.org/u/sumatorikki)\
**Replies:** 1\
**Last updated:** [June 22, 2022, 3:22pm UTC](https://community.drivendata.org/t/pretrained-models/7813 "2022-06-22T15:22:58Z")

</div>

Hello, everyone, I am very pleased that you have organised such an interesting competition. I have a question, because in the regulations in 2 places was ambiguously specified. Is it allowed to use pretreated models e.…
