# Of Pythons and Camels

DevFeed: [Of Pythons and Camels](<https://devfeed.tech/articles/of-pythons-and-camels-20197.md>)

Original publisher: [Read original article](<https://blog.janestreet.com/of-pythons-and-camels/>)

Author: Loren Puchalla Fiore

Published: 2019-07-09T00:00:00Z

Content type: tutorial

Language: en

Sources: [Jane Street](<https://devfeed.tech/sources/jane-street.md>)

Topics: [OCaml](<https://devfeed.tech/topics/ocaml.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Deep neural networks](<https://devfeed.tech/topics/deep-neural-networks.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [ImageNet](<https://devfeed.tech/topics/imagenet.md>)

Tags: [cpu](<https://devfeed.tech/tags/cpu.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [images](<https://devfeed.tech/tags/images.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ocaml](<https://devfeed.tech/tags/ocaml.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [training](<https://devfeed.tech/tags/training.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

## AI overview

This tutorial demonstrates transfer learning for image classification in OCaml, following the PyTorch Transfer Learning Tutorial. It uses a pretrained convolutional neural network and the Open Images Dataset V5 to classify images of pythons and camels, comparing fine-tuning with using the pretrained model as a feature extractor.

## Source excerpt

Welcome to another post in our series of how to use OCaml for machine learning. In previous posts we've discussed artistic style-transfer and reinforcement learning. If you haven't read these feel free to do so now, we'll wait right here until you're done. Ready? Ok, let's continue ...