Search Results for author:
Found 12 papers, 6 papers with code
A Partial Replication of MaskFormer in TensorFlow on TPUs for the TensorFlow Model Garden
Our implementation exploits the modular constructs available within the TensorFlow Model Garden (TFMG), encompassing elements such as the data loader, training orchestrator, and various architectural components, tailored and adapted to meet the specifications of the MaskFormer model.
PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models in Open-Source Software
Our analysis of this dataset provides the first summary statistics for the PTM supply chain, showing the trend of PTM development and common shortcomings of PTM package documentation.
PeaTMOSS: Mining Pre-Trained Models in Open-Source Software
Developing and training deep learning models is expensive, so software engineers have begun to reuse pre-trained deep learning models (PTMs) and fine-tune them for downstream tasks.
Naming Practices of Pre-Trained Models in Hugging Face
PTM authors should choose appropriate names for their PTMs, which would facilitate model discovery and reuse.
An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failures
In this study, we assessed the ability of Large Language Models (LLMs) to analyze historical software supply chain breaches.
Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem
We find that the node conversion stage of a model converter accounts for ~75% of the defects and 33% of reported failure are related to semantically incorrect models.
Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Vision
We describe this process as deep learning model reengineering.
An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry
We interviewed 12 practitioners from the most popular PTM ecosystem, Hugging Face, to learn the practices and challenges of PTM reuse.
Discrepancies among Pre-trained Deep Neural Networks: A New Threat to Model Zoo Reliability
Among the top 10 discrepancies, we find differences of 1. 23%-2. 62% in accuracy and 9%-131% in latency.
Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networks
We design a novel method that creates a parallel inference pipeline for computer vision problems that use hierarchical DNNs.
An Experience Report on Machine Learning Reproducibility: Guidance for Practitioners and TensorFlow Model Garden Contributors
To promote best practices within the engineering community, academic institutions and Google have partnered to launch a Special Interest Group on Machine Learning Models (SIGMODELS) whose goal is to develop exemplary implementations of prominent machine learning models in community locations such as the TensorFlow Model Garden (TFMG).
Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
At each node in the hierarchy, a small DNN identifies a different attribute of the query image.
