Fruits and Vegetables Recognition System Part-9 | Improving Deep Learning Model Performance
HTML-код
- Опубликовано: 11 сен 2024
- Hello and Welcome guys
In this project we'll learn how to make powerful deep learning model for 36 different classes of image
In this video,
We'll see how we can resolve the issue of underfitting and overfitting
We'll improve our fruits and vegetable model performance which we created in previous
Playlist Link: • Fruits and Vegetables ...
Project Link:
github.com/ani...
Dataset Link:
www.kaggle.com...
Hey, can we do Fruit Image recognition + freshness detection too i.e. like disease detection also ?
Btw thx for this video
Yes but for that we need to generate separate dataset using which we can train our model so that it can recognise freshness of fruits
is it really a pridiction???, i meant you have already kept the known images placed in a known folders and we are just giving direction to the code to compare from all the availble folder, what if we give an random image to this model which do not belongs to any folders, then wheather this is going to pridict that image also or not ?
i guess not? then what do we do for that type of pridiction ?
We are feeding neural networks those folder name in the form of label
All images of training set is x and corresponding folder name is y for each images
Thats how we are training it
As model is trained on 36 classes of images so it will recognise and do prediction on only these 36 classes of image
For front end which language will be used
Use streamlit for machine learning webapp development
That is the classification, not recognition, I think so
Yes the problem is classification
But our aim is to develop a model which can identify/recognise those classes
In that sense its recognition