CopyOnWriteArrayList的写操作与Vector的遍历操作性能消耗尤其严重，不推荐使用。 CopyOnWriteArrayLis

""" ResNet( (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace) (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) (layer1): Sequential( (0): BasicBlock( (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) (1): BasicBlock( (conv1): Conv2d(64, 64,

level: author: date: keyword: Paper: U2Net Summary design a two-level nested U-structure for salient object detection; capture more contextual information from different scales owing to the mixture of receptive fields of different sizes in ReSidual U-Blocks; increases the depth of the whole architecture without significantly increasing the computational cost owing to the the pooling operations. on the bottom level, we design a novel ReSidual U-block to extract intra-stage multi-scale features

A GAN has three primary components: a generator model for generating new data, a discriminator model for classifying whether generated data are real faces, or fake, and the adversarial network that pits them against each other. The problem of generating a new image of dog is equivalent to the problem of generating a new vector following the “dog probability distribu

utils：定义了加载数据等工具性的函数 layers：定义了模块如何计算卷积 models：定义了模型train train：包含了模型训练信息

15000万张短袖短裤识别数据 样例数据集：摄像头采集信息**（100张），供参赛者了解赛题典型场景数据，可用于编码调试； 训练数据集：摄像头采