GitHub

hoangtruong06/CNN-Convolution-Accelerator---Base-line-and-K-Multiplier-Architecture.

Convolutional Neural Networks (CNNs) are the backbone of modern image recognition. The key operation is 2D convolution: sliding a small filter (kernel) over an input image and computing weighted sums.
GitHub

test_op_nn_convolution.py

# with the License. You may obtain a copy of the License at # http://www.apache.org/licenses/LICENSE-2.0 x = relax.Var("x", R.Tensor((2, 3, 28), "float32")) w = relax ...
IEEE

SelfGCN: Graph Convolution Network With Self-Attention for Skeleton-Based Action Recognition

Abstract: Graph Convolutional Networks (GCNs) are widely used for skeleton-based action recognition and achieved remarkable performance. Due to the locality of graph convolution, GCNs can only utilize ...
IEEE

Graph Multi-Convolution and Attention Pooling for Graph Classification

Abstract: Many studies have achieved excellent performance in analyzing graph-structured data. However, learning graph-level representations for graph classification is still a challenging task.
生物通

AI增强计算机辅助设计：建模操作的预测建模

该研究提出一种基于图的CAD辅助方法，可在参数化设计序列中预测下一个建模操作。研究人员将来自汽车领域的真实CATIA V5模型转换为有向无环图（Directed Acyclic Graph，DAG）以捕获特征依赖关系，从而实现直接从结构设计数据中学习。所采用的 该研究提出一种基于图的CAD辅助方法，可在参数化设计序列中预测下一个建模操作。研究人员将来自汽车领域的真实CATIA V5模型转换为有向无 ...