Skip to content

mohammadroohian/flower_recognition_cnn_keras

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

flower_recognition_cnn_keras

Flower recognition with CNN and Keras

Dataset

https://www.kaggle.com/alxmamaev/flowers-recognition

Description

Context: This dataset contains 4242 images of flowers. The data collection is based on the data flicr, google images, yandex images. You can use this datastet to recognize plants from the photo.

Content: The pictures are divided into five classes: chamomile, tulip, rose, sunflower, dandelion. For each class there are about 800 photos. Photos are not high resolution, about 320x240 pixels. Photos are not reduced to a single size, they have different proportions!

Acknowledgements: The data collection is based on scraped data from flickr, google images, and yandex images.

Inspiration: What kind of flower is that?

Examples of suitable images for model learning:

image

Examples of challenging images for model learning:

image

How do different layers parse the image?

image

What parts of the images is the trained machine sensitive to?

image image image image image image image

What if the image is not a flower?

image

Releases

No releases published

Packages

No packages published

Languages