Comments (3)
- We need
model.interesting_tensors
(name tbd) if we want to automatically create visualizations
from lucid.
In "modelzoo/slim_models", the various models each provide a hard-coded list of layers.
E.g. MobilenetV2.py
MobilenetV2_10_slim.layers = _layers_from_list_of_dicts(MobilenetV2_10_slim, [
...
{'tags': ['conv'], 'name': 'MobilenetV2/expanded_conv_15/add', 'depth': 160},
{'tags': ['dense'], 'name': 'MobilenetV2/Predictions/Softmax', 'depth': 1001},
]
Is it possible to explain the reason these layers were selected?
Is it intending to be a list of the only layers in the graph worth visualizing?
Currently, I list all nodes in a graph (that I train myself) as text and then construct my own selections of layers to visualize. But this is tedious, and, of course, some nodes are inappropriate.
So I would appreciate a function that, given a graph node, generates a corresponding layer object (e.g.: as above) for every node, so I can filter a list of them for visualization. This is an admission of my own ignorance because I don't know how to get the depth from a node (nor tags, ['dense'] ?).
In general, I'm interested what makes a node "good" for visualization, and what makes one "bad".
from lucid.
That's a great question, @tul-urte!
The present list is created by a simple heuristic I wrote to find "interesting" nodes. It isn't perfect, but hopefully makes it easier for people to run lots of visualizations across models without thinking too much. I think it's basically looking for ReLu nodes, concat nodes, and add nodes (for resnets) and maybe trimming down some nodes in the resnet case.
There's some better (but very messy) code in lucid/scratch/pretty_graph/
that we're planning to clean up and reuse.
from lucid.
Related Issues (20)
- new style transfer error (just recently started happening) HOT 5
- How to visualize CLIP neurons using Lucid? HOT 2
- Transforms HOT 1
- Bug: AttributeError: module 'ctypes' has no attribute 'util' in glcontext.py, Line 58 HOT 1
- README image link is broken HOT 1
- ValueError: high is out of bounds for int32
- Blas GEMM launch failed HOT 1
- save show(VIS) to .jpeg HOT 1
- cover image missing HOT 1
- Dead link to Images
- 2d neural style transfer is completely broken
- I created a facebook group for Lucid
- I fixxed style transfer and deepdream notebooks
- Errors Ctypes HOT 4
- refixxed 2d neural transfer again.
- tutorial.ipynb is incompatible with Python 3 HOT 1
- I have fixxed feature attribution (100% fully working)
- Magic %tensorflow_version 1.x not supported in colab HOT 2
- Lucid library maintenance
- Columns and DataType Not Explicitly Set on line 83 of grid.py
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lucid.