captum
WeightWatcher
Our great sponsors
captum | WeightWatcher | |
---|---|---|
11 | 4 | |
4,568 | 1,392 | |
2.5% | 1.5% | |
8.6 | 9.2 | |
2 days ago | 15 days ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
captum
-
[D] [R] Research Problem about Weakly Supervised Learning for CT Image Semantic Segmentation
Most likely, NNs in general love shortcut learning (see Geirhos et al. 2020). In general, local explanations such as grad-cam are quite noisy, and sometimes even inconsistent (see Seo et al. 2018 ). Now, in my experience, I've seen that integrated gradients (see Sundararajan et al 2017) does a better job compared to Grad-CAM (also, add a noise tunnel), but this is only based on my limited experience. I would totally recommend using the implementations from the Captum library for loca explanations.
-
[D] Off-the-shelf image saliency scoring models?
Take a look at captum
-
Can you interrogate a machine learning model to find out why it gave certain predictions?
Sometimes. If explainable predictions are part of your business requirements, it's probably better not to rely entirely on black box models and instead design a system that gives you the information you need as part of it. If you end up using black box models, there are still methods that attempt to help attribute explanations to your prediction. Here's an example of a toolkit for attributing explanations post-hoc to black box model predictions: https://github.com/pytorch/captum
- [D] DL Practitioners, Do You Use Layer Visualization Tools s.a GradCam in Your Process?
-
What kind of explainability techniques exist for Reinforcement learning?
The straightforward way to interpret RL agent's decision is to use captum library.
-
[D] How do you choose which Black-Box Explainability method to use?
My use-case is research-oriented. I work on Explainable AI. Generally, the best package I've come across to compute attributions in Pytorch Captum. If your object detector is in PyTorch, you can perhaps build it in.
-
PyTorch vs. TensorFlow in 2022
Do any JAX experts know if there is an equivalent to https://captum.ai/ - a model interpretability library for pytorch?
In particular i want to be able to measure feature importance on both inputs and internal layers on a sample by sample basis. This is the only thing currently holding me back from using JAX right now.
Alternatively a simle to read/understand/port implementation of DeepLIFT would work too.
thanks
-
DeepLIFT or other explainable api implementations for JAX (like captum for pytorch)?
I'm interested to use JAX but am having a hard time finding anything similar to captum for the pytorch world.
- how to extract features from a (CNN) convolutional network having raw data with (XAI) explainable techinques?
-
Looking for help regarding explainable AI
Do you actually want to implement something? There are decent explainability libraries now, e.g., [AIX360](https://aix360.mybluemix.net/), [InterpretML](https://interpret.ml/), or [captum](https://captum.ai/). Pytorch + maybe pytorch lightning + captum might be the quickest way to actually implement something like an explainable neural net yourself. Do the standard tutorials for each of them and watch a few YT videos (or follow a coursera course or something like that) about how these things work in theory and practice, and you'll get up to speed relatively quickly. You will not be able to do useful work in ML without actually learning the ropes.
WeightWatcher
-
Ask HN: Have you seen anything original produced by generative AI?
These models are pretty much always extrapolating [0]
Whether the extrapolation is crude/low-rank or astute/high-rank is a question of memorization vs generalization. That gets into the question of whether or not the model is over-fitted or under-fitted. There are certain heuristics borrowed from high dimensional statistical physics that can be used to guess how good the test performance of a model will be on a typical task without even knowing what the test data is [1].
Originality for me means finding better answers to sub-tasks, and then combining those answers together in a better way. This is the nirvana of cross-entropy minimization - the emergence of capability results from gaining the ability to amass a wider range of skills, improving upon them, and percolating those improvements towards multiply the leverage of other skills.
How long such a thing can keep improving with current tech, who knows, but you should really think critically about whether that sounds just like interpolation through the corpus.
[0] Learning in High Dimension Always Amounts to Extrapolation - https://arxiv.org/abs/2110.09485
[1] https://github.com/CalculatedContent/WeightWatcher
-
Physics and Machine Learning
One of the things I love about physics is that, in addition to probably being my favorite of study in it's own right, it seems that a lot of the conceptual/mathematical content carries over and contributes to other fields. One example I've come across recently can be found here: https://github.com/CalculatedContent/WeightWatcher and here:
- [D] DL Practitioners, Do You Use Layer Visualization Tools s.a GradCam in Your Process?
- A New Link to an Old Model Could Crack the Mystery of Deep Learning
What are some alternatives?
shap - A game theoretic approach to explain the output of any machine learning model.
TorchDrift - Drift Detection for your PyTorch Models
DALEX - moDel Agnostic Language for Exploration and eXplanation
pytea - PyTea: PyTorch Tensor shape error analyzer
lucid - A collection of infrastructure and tools for research in neural network interpretability.
cockpit - Cockpit: A Practical Debugging Tool for Training Deep Neural Networks
flax - Flax is a neural network library for JAX that is designed for flexibility.
explainerdashboard - Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
Transformer-MM-Explainability - [ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.
alibi - Algorithms for explaining machine learning models
cleverhans - An adversarial example library for constructing attacks, building defenses, and benchmarking both