Name		Name	Last commit message	Last commit date
parent directory ..
data		data
images		images
nltk_data		nltk_data
support_files		support_files
.gitignore		.gitignore
C3_W4_Assignment.ipynb		C3_W4_Assignment.ipynb
C3_W4_lecture_nb_1_siamese.ipynb		C3_W4_lecture_nb_1_siamese.ipynb
C3_W4_lecture_nb_2_Modified_Triplet_Loss.ipynb		C3_W4_lecture_nb_2_Modified_Triplet_Loss.ipynb
C3_W4_lecture_nb_3_accuracy.ipynb		C3_W4_lecture_nb_3_accuracy.ipynb
README.md		README.md
model.pkl.gz		model.pkl.gz
w4_unittest.py		w4_unittest.py

README.md

Siamese Networks

Creating a Siamese Model using Trax

Trax allows to define neural network architectures by stacking layers (similarly to other libraries such as Keras). In this ungraded lab you will see how a Siamese model can be created using Trax.
Modified Triplet Loss

In this notebook you'll see how to calculate the full triplet loss, step by step, including the mean negative and the closest negative. You'll also calculate the matrix of similarity scores.
Evaluate a Siamese Model

In this lecture notebook you will learn how to evaluate a Siamese model using the accuracy metric using data from this week's assignment.