microsoft/AI-For-Beginners

Public

mirrored fromhttps://github.com/microsoft/AI-For-BeginnersAvailable

CodeCommitsIssuesPull requestsActionsInsightsSecurity
c8ea72ffc7b305f3e74f779ed24791a4651c2161

Branches

Tags

  • No tags available.
0Branches0Tags
Go to file
Add file
Code

Clone

HTTPS

Download ZIP

lessons/4-ComputerVision/07-ConvNets/lab/README.md

31lines · modecode

1# Classification of Pets Faces
2
3Lab Assignment from [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
4
5## Task
6
7Imagine 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. This can be successfully done using neural networks.
8
9You need to train a convolutional neural network to classify different breeds of cats and dogs using **Pet Faces** dataset.
10
11## The Dataset
12
13We will use the **Pet Faces** dataset, derived from [Oxford-IIIT](https://www.robots.ox.ac.uk/~vgg/data/pets/) pets dataset. It contains 35 different breeds of dogs and cats.
14
15![Dataset we will deal with](images/data.png)
16
17To download the dataset, use this code snippet:
18
19```python
20!wget https://mslearntensorflowlp.blob.core.windows.net/data/petfaces.tar.gz
21!tar xfz petfaces.tar.gz
22!rm petfaces.tar.gz
23```
24
25## Stating Notebook
26
27Start the lab by opening [PetFaces.ipynb](PetFaces.ipynb)
28
29## Takeaway
30
31You have solved a relatively complex problem of image classification from scratch! There were quite a lot of classes, and you were still able to get reasonable accuracy! It also makes sense to measure top-k accuracy, because it is easy to confuse some of the classes which are not clearly different even to human beings.
32