The Data Frog keras

dessin_transfer_learning_crop2.jpg

Image Recognition with Transfer Learning (98.5%)

Learn how to use transfer learning to easily classify dog and cat pictures with a 98.5% accuracy. Notebook ready to run on your machine.

Read More →

images/2019/09/datafrog_chien_chat-2.jpg

Image Recognition: Dogs vs Cats! (92%)

Learn how to build a deep convolutional neural network from scratch to classify dog and cat pictures with a 92% accuracy, without transfer learning. Notebook ready to run on your machine.

Read More →

images/2019/03/Yelp-5-Star.png

Sentiment Analysis with a deep convolutional network (yelp dataset part 3)

Sentiment analysis is an important application of natural language processing, as it makes it possible to predict what a person thinks given the text she has written. Let's do that with a deep convolutional network on the large yelp dataset.

Read More →

images/2019/03/seagal.jpg

Word Embedding and Sentiment Analysis (IMDB)

Word embedding is essential in natural language processing with deep learning. This technique allows the network to learn about the meaning of the words. In this post, we classify movie reviews in the IMDB dataset as positive or negative, and provide a visual illustration of embedding.

Read More →

images/2019/02/conv_layer_schema.png

Tuning a Deep Convolutional Network for Image Recognition, with keras and TensorFlow

You would like to try deep learning but don't have a GPU? Or you don't want to install software on your computer? This tutorial is for you, as it requires no specific hardware or software.

Read More →

images/2019/02/neuralnet_3d_lison.jpg

First Neural Network with Keras

Keras is the easiest and most powerful way to deal with neural networks in python. Give it a try by training your first neural net to classify handwritten digits

Read More →

  • 1