pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图;欢迎试用、关注并反馈问题...
-
Updated
Jan 13, 2021 - Python
#
model-interpretability
Here are 67 public repositories matching this topic...
Class Activation Map (CAM) Visualizations in PyTorch.
-
Updated
May 20, 2020 - Python
surrogate quantitative interpretability for deepnets
motif-analysis surrogate-modelling explainable-ai model-interpretability attribution-methods regulatory-genomics
-
Updated
Aug 28, 2026 - Python
Official repository for the paper "Instance-wise Causal Feature Selection for Model Interpretation" (CVPRW 2021)
-
Updated
May 29, 2021 - Python
This article explores the theory behind explainable car pricing using value decomposition, showing how machine learning models can break a predicted price into intuitive components such as brand premium, age depreciation, mileage influence, condition effects, and transmission or fuel-type adjustments.
random-forest predictive-modeling sensitivity-analysis machine-learning-theory interpretable-ml explainable-ai model-interpretability economic-modeling feature-attribution applied-ml consumer-analytics value-decomposition data-science-methods transparent-ai pricing-intelligence automotive-analytics car-price-modeling ml-explainability automotive-ml explainable-pricing
-
Updated
Oct 1, 2026 - Python
Code for "Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability" (https://arxiv.org/abs/2010.09750)
-
Updated
Nov 10, 2020 - Python
Explainable AI (XAI) based system for detecting financial fraud using machine learning, with model interpretability, analysis, and research-backed implementation.
python data-science machine-learning scikit-learn classification fraud-detection feature-importance explainable-ai xai shap model-interpretability financial-fraud
-
Updated
Apr 14, 2026 - Python
Universal probing and interpretability tool for MLX language models on Apple Silicon
mlx mixture-of-experts model-interpretability ablation-studies mechanistic-interpretability llm-inference llm-evaluation ai-interpretability apple-intelligence expert-routing gpt-oss-20b mlx-llms
-
Updated
Jan 28, 2026 - Python
Implementation of the Grad-CAM algorithm in an easy-to-use class, optimized for transfer learning projects and written using Keras and Tensorflow 2.x
python deep-learning tensorflow transfer-learning interpretability gradcam model-interpretability tensorflow2
-
Updated
May 19, 2021 - Python
A lightweight hook-based analysis utility for PyTorch modules. Gradients, forward and backward activations and more.
-
Updated
Aug 4, 2026 - Python
🔍 Enhance medical imaging with a lightweight CNN model that offers over 91% accuracy and integrated explainability for better clinical trust.
ai computer-vision deep-learning cnn pytorch medical-imaging pathology explainable-ai model-interpretability edge-ai integrated-gradients captum ml-for-health healthcare-ai lightweight-model open-source-ai pathmnist scalable-ai
-
Updated
Oct 3, 2026 - Python
A lightweight Explainable AI CNN for PathMNIST medical imaging, achieving 91%+ accuracy with Integrated Gradients and SQLite-based attribution storage. Built in PyTorch, this scalable model delivers high performance, transparency, and real-world readiness, making it ideal for medical AI, edge deployment, and explainable deep learning research.
ai computer-vision deep-learning sqlite cnn pytorch medical-imaging pathology explainable-ai model-interpretability edge-ai integrated-gradients medical-ai captum ml-for-health healthcare-ai lightweight-model open-source-ai pathmnist scalable-ai
-
Updated
Sep 13, 2025 - Python
squid repository for manuscript analysis
motif-analysis surrogate-modelling explainable-ai model-interpretability attribution-methods regulatory-genomics
-
Updated
Mar 5, 2024 - Python
🐍 Miru — Multimodal reasoning tracer 👁️. Answers questions over images/docs 🖼️📄 while visualizing step-by-step attention and reasoning 🔍. Built for explainable vision-language AI 🤖✨
python open-source computer-vision deep-learning transformers attention reasoning vlm saliency image-understanding multimodal xai mlops explainability model-interpretability fastapi document-ai llm vision-language-models ai-visualization
-
Updated
Jul 25, 2026 - Python
IEEE-CIS 电商支付反欺诈：EDA→WOE/LR基线→LightGBM (测试集 AUC 0.8997 / KS 0.6501)→SHAP→三层策略→8条规则库，含23单测与推理入口
python machine-learning jupyter-notebook credit-card-fraud kaggle lightgbm data-analysis feature-engineering fraud-detection anti-fraud risk-control shap model-interpretability imbalanced-classification
-
Updated
Sep 1, 2026 - Python
Lightweight Python library for interactive demo and inspection of recommender systems in Streamlit.
information-retrieval reproducible-research collaborative-filtering learning-to-rank recsys recommender-system recommendation-algorithms movielens goodbooks-10k model-interpretability sequential-recommendation streamlit offline-evaluation
-
Updated
Aug 22, 2026 - Python
Dual-stream deepfake detector in PyTorch: ConvNeXt-Small spatial stream + ResSE-Spectral Tower (SRM/Bayar/FFT) frequency stream with SNR-adaptive gating, fused into a Bi-GRU video head. Zero-leakage identity splits, calibrated 3-zone thresholds, Grad-CAM diagnostics. Video AUC 0.872, LOTO macro-AUC 0.897, 60.9 FPS on T4.
opencv computer-vision grad-cam pytorch pytest networkx graph-partitioning torchvision model-interpretability deepfake-detection streamlit convnext huggingface-spaces dual-stream gated-fusion fft-spectrum spatial-rich-model bayar-stamm temperature-calibration loss-masking
-
Updated
Oct 2, 2026 - Python
Scripts and trained models from our paper: M. Ntrougkas, N. Gkalelis, V. Mezaris, "T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers", IEEE Access, 2024. DOI:10.1109/ACCESS.2024.3405788.
-
Updated
Sep 18, 2024 - Python
code and difference of resolution for visualizing the loss landscape of a GAN and understanding what a loss landscape is
python machine-learning research deep-learning neural-network gan 3d-visualization 3d-graph model-interpretability loss-landscape
-
Updated
Aug 16, 2026 - Python
Powerful Python tool for visualizing and interacting with pre-trained Masked Language Models (MLMs) like BERT. Features include self-attention visualization, masked token prediction, model fine-tuning, embedding analysis with PCA/t-SNE, and SHAP-based model interpretability.
python nlp machine-learning deep-learning tensorflow bert model-visualization self-attention shap model-interpretability huggingface transformer-models masked-language-models model-fine-tuning
-
Updated
Oct 24, 2024 - Python
Add this topic to your repo
To associate your repository with the model-interpretability topic, visit your repo's landing page and select "manage topics."