mirrors/rocm_jax
1
0
Fork 0
mirror of https://github.com/ROCm/jax.git synced 2025-04-18 21:06:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

add Generative Modelling by Estimating Gradients of Data Distribution notebook tutorial

Browse Source
This commit is contained in:
Denis Mazur 2019-08-07 22:02:02 +03:00
parent a6ec5a916c
commit 52e7c23e44
3 changed files with 820 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -91,7 +91,8 @@ And for a deeper dive into JAX:
- [Common gotchas and sharp edges](https://colab.research.google.com/github/google/jax/blob/master/notebooks/Common_Gotchas_in_JAX.ipynb)
- [The Autodiff Cookbook, Part 1: easy and powerful automatic differentiation in JAX](https://colab.research.google.com/github/google/jax/blob/master/notebooks/autodiff_cookbook.ipynb)
- [Directly using XLA in Python](https://colab.research.google.com/github/google/jax/blob/master/notebooks/XLA_in_Python.ipynb)
- [MAML Tutorial with JAX](https://colab.research.google.com/github/google/jax/blob/master/notebooks/maml.ipynb).
- [MAML Tutorial with JAX](https://colab.research.google.com/github/google/jax/blob/master/notebooks/maml.ipynb)
- [Generative Modeling by Estimating Gradeints of Data Distribution in JAX](https://colab.research.google.com/github/google/jax/blob/master/notebooks/score-matching.ipynb).
## Installation
JAX is written in pure Python, but it depends on XLA, which needs to be compiled

4
notebooks/README.md
View File

@ -8,6 +8,8 @@ Use the links below to open any of these for interactive exploration in colab.
- [MAML][maml] - pedagogical demonstration of Model-Agnostic Meta-Learning in JAX.
- [Score Matching][gmegdd] - demonstration of Generative Modeling by Estimating Gradients of the Data Distribution
- [vmapped log-probabilities][vmapped log-probs] - demonstrates the utility of __vmap__ for Bayesian inference.
- [gufuncs via vmap][gufuncs] - how to implement NumPy-like gufuncs using __vmap__.
@ -20,10 +22,12 @@ Use the links below to open any of these for interactive exploration in colab.
[quickstart]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/quickstart.ipynb
[Common_Gotchas_in_JAX]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/Common_Gotchas_in_JAX.ipynb
[gufuncs]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/gufuncs.ipynb
[maml]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/maml.ipynb
[gmegdd]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/score-matching.ipynb
[vmapped log-probs]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/vmapped%20log-probs.ipynb
[neural_network_with_tfds_data]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/neural_network_with_tfds_data.ipynb
[neural_network_and_data_loading]:https://colab.sandbox.google.com/github/google/jax/blob/master/notebooks/neural_network_and_data_loading.ipynb

814
notebooks/score_matching.ipynb Normal file
View File

File diff suppressed because one or more lines are too long