microsoft/AI-For-Beginners

Public

6c2953e954e3bbc8d54db06124aac4fd78db2ebc

Find a branch or tag

HTTPS

4-ComputerVision/08-TransferLearning/lab/README.md

29lines · modecode

unknown

1	`# Classification of Oxford Pets using Transfer Learning`
2
3	`Lab Assignment from [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).`
4
5	`## Task`
6
7	`Imagine you need to develop and application for pet nursery to catalog all pets. One of the great features of such an application would be automatically discovering the breed from a photograph. In this assignment, we will use transfer learning to classify real-life pet images from [Oxford-IIIT](https://www.robots.ox.ac.uk/~vgg/data/pets/) pets dataset.`
8
9	`## The Dataset`
10
11	`We will use the original [Oxford-IIIT](https://www.robots.ox.ac.uk/~vgg/data/pets/) pets dataset, which contains 35 different breeds of dogs and cats.`
12
13	`To download the dataset, use this code snippet:`
14
15	```python
16	`!wget https://mslearntensorflowlp.blob.core.windows.net/data/oxpets_images.tar.gz`
17	`!tar xfz oxpets_images.tar.gz`
18	`!rm oxpets_images.tar.gz`
19	```
20
21	`## Stating Notebook`
22
23	`Start the lab by opening [OxfordPets.ipynb](OxfordPets.ipynb)`
24
25
26	`## Takeaway`
27
28	`Transfer learning and pre-trained networks allow us to solve real-world image classification problems relatively easily. However, pre-trained networks work well on images of similar kind, and if we start classifying very different images (eg. medical images), we are likely to get much worse results.`
29
30