mirror of
https://github.com/Andreaierardi/Master-DataScience-Notes.git
synced 2025-01-28 20:27:37 +01:00
28 lines
2.4 KiB
Markdown
28 lines
2.4 KiB
Markdown
# Machine-Learning-Project
|
|
|
|
Project [Links](https://docs.google.com/document/d/e/2PACX-1vTqeS0WmZDMvxuN8auSIvAVncNg7zSR73Ibz6XaAKOjk7W3QJsAN4j6kJKUZN156f0y1_BUyrgiJSQk/pub).
|
|
|
|
# Contributors :busts_in_silhouette:
|
|
- Andrea Ierardi <a href="https://www.linkedin.com/in/andreaierardi/" rel="nofollow noreferrer">
|
|
<img src="https://i.stack.imgur.com/gVE0j.png" alt="linkedin"> LinkedIn
|
|
</a>
|
|
<a href="https://github.com/Andreaierardi" rel="nofollow noreferrer"> <img src="https://i.stack.imgur.com/tskMh.png" alt="github"> Github </a>
|
|
<a href="https://ierardiandrea.com/" rel="nofollow noreferrer"> <img src="https://github.com/Andreaierardi/Master-DataScience-Notes/blob/master/img/website.svg" width=15> Website </a>
|
|
|
|
- Emanuele Morales <a href="https://www.linkedin.com/in/emanuele-morales-320604180/" rel="nofollow noreferrer">
|
|
<img src="https://i.stack.imgur.com/gVE0j.png" alt="linkedin"> LinkedIn
|
|
</a>
|
|
<a href="https://github.com/emanuelemorales" rel="nofollow noreferrer"> <img src="https://i.stack.imgur.com/tskMh.png" alt="github"> Github </a>
|
|
|
|
- Gregorio Saporito <a href="https://www.linkedin.com/in/greg-saporito/" rel="nofollow noreferrer">
|
|
<img src="https://i.stack.imgur.com/gVE0j.png" alt="linkedin"> LinkedIn
|
|
</a>
|
|
<a href="https://github.com/gregorio-saporito" rel="nofollow noreferrer"> <img src="https://i.stack.imgur.com/tskMh.png" alt="github"> Github </a>
|
|
|
|
|
|
# Assignment
|
|
**Image classification with Neural Networks**: Use [Tensorflow 2](https://www.tensorflow.org/) to train neural networks for the classification of fruit/vegetable **types** based on images from [this dataset](https://www.kaggle.com/moltean/fruits). Images must be transformed from JPG to RGB pixel values and scaled down (e.g., 32x32). Use fruit/vegetable types (as opposed to variety) as labels to predict and consider only the 10 most frequent types (apple, banana, plum, pepper, cherry, grape, tomato, potato, pear, peach). Experiment with different network architectures and training parameters documenting their influence of the final predictive performance. While the training loss can be chosen freely, the reported test errors must be measured according to the zero-one loss for multiclass classification.
|
|
|
|
If you are not familiar with neural networks for image classification, take one of the many [tutorials](https://www.tensorflow.org/tutorials) available in Tensorflow.
|
|
|