Standardized Serverless ML Inference Platform on Kubernetes

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...

Class Activation Map (CAM) Visualizations in PyTorch.

surrogate quantitative interpretability for deepnets

Official repository for the paper "Instance-wise Causal Feature Selection for Model Interpretation" (CVPRW 2021)

Code for "Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability" (https://arxiv.org/abs/2010.09750)

squid repository for manuscript analysis

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

🎯 Deep Learning Model Analysis Made Easy: Visualize and understand your model's behavior, attention patterns, and decision boundaries with interactive visualizations.

Exercise on interpretability with integrated gradients.

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.

Sentiment Analysis using Machine Learning

Investigating a neural network response to input parameters using sensitivity analysis techniques.

Federated Learning Simulation on a Single GPU with Model Interpretability and Interactive Visualization

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.