在 WSL2（Ubuntu 环境）中，当对形状为 [3, 2, 2] 的张量执行 paddle.nn.Softmax(dim=-3) 时，会触发 Segmentation Fault。 此问题可复现，且不会在 PyTorch / TensorFlow / MindSpore 中出现，疑似 PaddlePaddle 在 softmax kernel 内部对 shape 或维度处理存在 bug。

Meta Platforms Inc. today is expanding its suite of open-source Segment Anything computer vision models with the release of SAM 3 and SAM 3D, introducing enhanced object recognition and ...

Abstract: ReRAM-based Processor-In-Memory (PIM) architectures have demonstrated their ability to accelerate the matrix multiplication performed by the Transformer. However, these approaches often ...

Researchers from Science Tokyo develop a Multi-scale Hessian-enhanced Patch-based Neural Network Model for Segmentation of Liver Tumor from CT Scans. Liver cancer is the sixth most common cancer ...

ABSTRACT: This study addresses the growing demand for news text classification driven by the rapid expansion of internet information by proposing a classification algorithm based on a Bidirectional ...

Accurate segmentation of leaf diseases is crucial for crop health management and disease prevention. However, existing studies fall short in addressing issues such as blurred disease spot boundaries ...

Underwater images segmentation is essential for tasks such as underwater exploration, marine environmental monitoring, and resource development. Nevertheless, given the complexity and variability of ...