Тёмный

t-SNE Dimensionality Reduction with Scikit-Learn 

Nono Martínez Alonso
Подписаться 3,5 тыс.
Просмотров 1,8 тыс.
50% 1

How to encode an image dataset to reduce its dimensionality and visualize it in the 2D space.
🐍 Colab Notebook colab.research.google.com/dri...
💬 Join the conversation on Discord / discord
🧠 Machine Intelligence Playlist: • 🧠 Machine Intelligence
🔴 Live Playlist: • 🧠 Live Streams
🕸 Web Development Playlist: • 🚀 Web
🍃 Getting Simple: gettingsimple.com
🎙 Podcast: gettingsimple.com/podcast
🗣 Ask Questions: gettingsimple.com/ask
💬 Discord: / discord
👨🏻‍🎨 Sketches: sketch.nono.ma
✍🏻 Blog: nono.ma
🐦 Twitter: / nonoesp
📸 Instagram: / nonoesp
==================
🎥 VIDEO CHAPTERS
==================
00:00 Introduction
02:02 Problem overview
05:46 Dataset
06:51 Steps
07:22 Colab notebook outline
08:49 Uploading our dataset to Colab
10:45 Dataset loading
19:48 Recap
20:05 Dataset loading (manually)
21:45 Dataset loading (without tf.data)
30:00 Plotting 28x28 images and 30-digit codings
31:29 Training for different steps
37:40 Coding and decoding
41:30 Training on the sketches dataset
45:03 Dataset scatterplot with scikit-learn t-SNE
50:43 Render images in the scatterplot
57:20 Call to Action

Наука

Опубликовано:

 

10 июл 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 6   
@annyd3406
@annyd3406 Год назад
no one explains t-sne thank you that's a rare video !!!!
Год назад
Thanks for your comment, Anny! I'm glad you found this explanation useful. =) Kindly, Nono
@jackiexu3683
@jackiexu3683 Год назад
That is amazing! May I know do we have the link for the jupyter notebook or google colab file?
Год назад
Hi, Jackie! 🐍 Colab Notebook › colab.research.google.com/drive/1vKFJehl-o2AhOajz9fxxwiIbQ4jwp6Vc?usp=sharing Thanks for the comment, I forgot to link the notebook from the video notes. Let me know if that works! Kindly, Nono
@jackiexu3683
@jackiexu3683 11 месяцев назад
Detailed Summary: [00:00](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Tutorial on dimensionality reduction using t-SNE with scikit-learn - Using stacked autoencoders to obtain codings for input images - Visualizing the reduced dimensions with t-SNE and plotting for understanding similarities [09:23](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Loading and processing small image dataset in TensorFlow. - Data gets deleted when the runtime is recycled on Colab. - Process small image dataset using TensorFlow and load in the same format as larger dataset. [17:00](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Loading and preprocessing dataset for dimensionality reduction - Batching and converting RGB images to grayscale - Loading manually using Glob and PIL libraries [24:08](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Implemented encoder-decoder architecture for image classification - Trained the model with 40 epochs and achieved 98.16% accuracy - Generated images using the trained model and plotted input and output images [31:09](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Implemented and trained a deep learning model for image generation - The model was trained on a custom dataset and achieved 99.32% accuracy - Generated images using the trained decoder and observed changes in codings [37:29](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Generative model trained for longer refines results - Training for more epochs shows improvements in codings - Small changes in codings significantly alter resulting image [44:08](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Testing clustering and dimensionality reduction algorithms - Experimented with t-SNE and plotted results in scatterplot - Visualized scatterplot with images to see clustering of drawings [51:23](ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-DtFQAJmlID0.html) Visualizing similarity on Fashion MNIST - t-SNE plots can group similar images together - This can be used for recommendation systems
11 месяцев назад
That's awesome - did you auto-generate it?
Далее
TensorFlow with Docker in 5 MINUTES
5:36
Просмотров 16 тыс.
На чем играют ПРО | Standoff 2
07:25
Просмотров 185 тыс.
УНИТАЗ В ЛЕСУ?? #shorts
00:24
Просмотров 803 тыс.
t-SNE Simply Explained
25:49
Просмотров 11 тыс.
Autoencoders | Deep Learning Animated
11:41
Просмотров 3,4 тыс.
t-SNE
11:01
Просмотров 2,6 тыс.
MLX for Apple Silicon - Creative AI with Nono · Live 109
1:30:51
StatQuest: t-SNE, Clearly Explained
11:48
Просмотров 454 тыс.
Самый дорогой кабель Apple
0:37
Просмотров 329 тыс.