Convolutional Neural Networks with Alternately Updated Clique

具体代码见:https://github.com/iboing/CliqueNet

class build_cliquenet(nn.Module):def __init__(self, input_channels, list_channels, list_layer_num, if_att):super(build_cliquenet, self).__init__()self.fir_trans = nn.Conv2d(3, input_channels, kernel_size=7, stride=2, padding=3, bias=False)self.fir_bn = nn.BatchNorm2d(input_channels)self.fir_pool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.block_num = len(list_channels)self.if_att = if_attself.list_block = nn.ModuleList()self.list_trans = nn.ModuleList()self.list_gb = nn.ModuleList()self.list_gb_channel = []self.list_compress = nn.ModuleList()input_size_init = 56for i in xrange(self.block_num):if i == 0:self.list_block.append(clique_block(input_channels=input_channels, channels_per_layer=list_channels[0], layer_num=list_layer_num[0], loop_num=1, keep_prob=0.8))self.list_gb_channel.append(input_channels + list_channels[0] * list_layer_num[0])else :self.list_block.append(clique_block(input_channels=list_channels[i-1] * list_layer_num[i-1], channels_per_layer=list_channels[i], layer_num=list_layer_num[i], loop_num=1, keep_prob=0.8))self.list_gb_channel.append(list_channels[i-1] * list_layer_num[i-1] + list_channels[i] * list_layer_num[i])if i < self.block_num - 1:self.list_trans.append(transition(self.if_att, current_size=input_size_init, input_channels=list_channels[i] * list_layer_num[i], keep_prob=0.8))self.list_gb.append(global_pool(input_size=input_size_init, input_channels=self.list_gb_channel[i] // 2))self.list_compress.append(compress(input_channels=self.list_gb_channel[i], keep_prob=0.8))input_size_init = input_size_init // 2self.fc = nn.Linear(in_features=sum(self.list_gb_channel) // 2, out_features=1000)for m in self.modules():if isinstance(m, nn.Conv2d):n = m.kernel_size[0] * m.kernel_size[1] * m.out_channelsm.weight.data.normal_(0, math.sqrt(2. / n))elif isinstance(m, nn.BatchNorm2d):m.weight.data.fill_(1)m.bias.data.zero_()elif isinstance(m, nn.Linear):m.bias.data.zero_()

class clique_block(nn.Module):def __init__(self, input_channels, channels_per_layer, layer_num, loop_num, keep_prob):super(clique_block, self).__init__()self.input_channels = input_channelsself.channels_per_layer = channels_per_layerself.layer_num = layer_numself.loop_num = loop_numself.keep_prob = keep_prob# conv 1 x 1self.conv_param = nn.ModuleList([nn.Conv2d(self.channels_per_layer, self.channels_per_layer, kernel_size = 1, padding = 0, bias = False)for i in range((self.layer_num + 1) ** 2)])for i in range(1, self.layer_num + 1):self.conv_param[i] = nn.Conv2d(self.input_channels, self.channels_per_layer, kernel_size = 1, padding = 0, bias = False)for i in range(1, self.layer_num + 1):self.conv_param[i * (self.layer_num + 2)] = Nonefor i in range(0, self.layer_num + 1):self.conv_param[i * (self.layer_num + 1)] = Noneself.forward_bn = nn.ModuleList([nn.BatchNorm2d(self.input_channels + i * self.channels_per_layer) for i in range(self.layer_num)])self.forward_bn_b = nn.ModuleList([nn.BatchNorm2d(self.channels_per_layer) for i in range(self.layer_num)])self.loop_bn = nn.ModuleList([nn.BatchNorm2d(self.channels_per_layer * (self.layer_num - 1)) for i in range(self.layer_num)])self.loop_bn_b = nn.ModuleList([nn.BatchNorm2d(self.channels_per_layer) for i in range(self.layer_num)])# conv 3 x 3self.conv_param_bottle = nn.ModuleList([nn.Conv2d(self.channels_per_layer, self.channels_per_layer, kernel_size = 3, padding = 1, bias = False)for i in range(self.layer_num)])

Convolutional Neural Networks with Alternately Updated Clique相关推荐

深度模型压缩论文（01）- Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks
文章目录 1.摘要和介绍 1.1摘要部分 2.背景和方法 2.1 背景 2.2 贡献 2.3 方法 3.实验和结果 3.1 实验 3.2 结果 4.总结和展望 4.1 总结 4.2 展望本系列是在阅 ...
DEEPCON: protein contact prediction using dilated convolutional neural networks with dropout
今天真的要开始正式进入科研状态了,之前一直都进入失败,咳!那就先来看一篇相关领域的论文吧 ---------------------------------------------- 题目:DEEPC ...
keras构建卷积神经网络（CNN(Convolutional Neural Networks)）进行图像分类模型构建和学习
keras构建卷积神经网络(CNN(Convolutional Neural Networks))进行图像分类模型构建和学习全连接神经网络(Fully connected neural networ ...
Graph Convolutional Neural Networks for Predicting Drug-Target Interactions
1. 摘要 2. 数据集 DUDE数据集改进 DUDE-chemBl负样本数据集最大无偏数据集(MUV) 3. 图构建 pocket graph molecuar graph 4. 口袋pretra ...
【文本分类】Deep Pyramid Convolutional Neural Networks for Text Categorization
·阅读摘要: 本文提出了DPCNN(深度金字塔CNN)模型.在transformer.bert还没兴起的年代,模型越深效果越好,但是模型的复杂度会随着深度提升.粗略地说,DPCNN就是为了解决CN ...
【文本分类】Recurrent Convolutional Neural Networks for Text Classification
·摘要: 从模型的角度,本文作者将RNN(Bi-LSTM)和max_pooling结合使用,提出RCNN模型,应用到了NLP的文本分类任务中,提高了分类精度. ·参考文献: [1] Recur ...
【文本分类】Convolutional Neural Networks for Sentence Classification
·摘要: 本文作者将CNN引用到了NLP的文本分类任务中. ·参考文献: [1] Convolutional Neural Networks for Sentence Classificati ...
量化网络训练--Towards Effective Low-bitwidth Convolutional Neural Networks
Towards Effective Low-bitwidth Convolutional Neural Networks CVPR2018 https://github.com/nowgood/Qua ...
二值网络--XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks ECCV2016 http://allenai ...

Convolutional Neural Networks with Alternately Updated Clique

Convolutional Neural Networks with Alternately Updated Clique相关推荐

最新文章

热门文章