0. 执行过程 查询语句的执行流程如下：权限校验（如果命中缓存）—>查询缓存—>分析器—>优

1. ResMLP ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically across channels, and (ii) a two-layer feed-forward network in which channels interact independently per patch. When trained with a modern training strategy using heavy data-augmentation and optionally distillation, it attains surprisingly good accuracy/complexity trade-offs on ImageNet. 2.

1. 控制反转(IoC)和依赖注入(DI) IoC(Inversion of Control,控制反转) 是Spring 中一个非常非常重要的概念，它不是什么技术，而是一种解耦的设

Chaton, Thomas, et al. “Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds.” arXiv preprint arXiv:2010.04642 (2020). [pdf] [code]

论文对GNN模型分类如下： 图卷积网络(Graph convolutional networks)和图注意力网络(graph attention networks)，因为涉及到传播步骤(pr

0. python统计函数 import numpy as np layerData = np.loadtxt(open('./data/layer_test_acc.csv', "r"), delimiter=",", skiprows=1,dtype=str) import seaborn as sns from sklearn.metrics import confusion_matrix import matplotlib.pyplot as plt sns.set() from sklearn.metrics import precision_score from sklearn.metrics import recall_score print(len(ground),len(predict)) C2= confusion_matrix(ground, predict, labels=[0,1]) #print(ground) #print(C2) #https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html result=C2.ravel() print(C2.ravel(),C2.ravel()/len(ground)) print("speed:{}- layer:{}- distance:{} -slop:{} -accuracy:{} -TN:{} -FP:{} -FN:{} -TP:{} -Pr:{} -Recal:{}".format(0.15,2,0.3,0,count/len(ground),result[0],result[1],result[2],result[3],precision_score(ground,predict),recall_score(ground,predict))) sns.heatmap(C2,annot=True) # f, (ax1,ax2) = plt.subplots(figsize =