您好,登錄后才能下訂單哦!
這篇文章主要介紹pytorch網(wǎng)絡(luò)層結(jié)構(gòu)數(shù)組化的示例分析,文中介紹的非常詳細(xì),具有一定的參考價(jià)值,感興趣的小伙伴們一定要看完!
最近再寫openpose,它的網(wǎng)絡(luò)結(jié)構(gòu)是多階段的網(wǎng)絡(luò),所以寫網(wǎng)絡(luò)的時(shí)候很想用列表的方式,但是直接使用列表不能將網(wǎng)絡(luò)中相應(yīng)的部分放入到cuda中去。
其實(shí)這個(gè)問題很簡單的,使用moduleList就好了。
1 我先是定義了一個(gè)函數(shù),用來根據(jù)超參數(shù),建立一個(gè)基礎(chǔ)網(wǎng)絡(luò)結(jié)構(gòu)
stage = [[3, 3, 3, 1, 1], [7, 7, 7, 7, 7, 1, 1]] branches_cfg = [[[128, 128, 128, 512, 38], [128, 128, 128, 512, 19]], [[128, 128, 128, 128, 128, 128, 38], [128, 128, 128, 128, 128, 128, 19]]] # used for add two branches as well as adapt to certain stage def add_extra(i, branches_cfg, stage): """ only add CNN of brancdes S & L in stage Ti at the end of net :param in_channels:the input channels & out :param stage: size of filter :param branches_cfg: channels of image :return:list of layers """ in_channels = i layers = [] for k in range(len(stage)): padding = stage[k] // 2 conv2d = nn.Conv2d(in_channels, branches_cfg[k], kernel_size=stage[k], padding=padding) layers += [conv2d, nn.ReLU(inplace=True)] in_channels = branches_cfg[k] return layers
2 然后用普通列表裝載他們
conf_bra_list = [] paf_bra_list = [] # param for branch network in_channels = 128 for i in range(all_stage): if i > 0: branches = branches_cfg[1] conv_sz = stage[1] else: branches = branches_cfg[0] conv_sz = stage[0] conf_bra_list.append(nn.Sequential(*add_extra(in_channels, branches[0], conv_sz))) paf_bra_list.append(nn.Sequential(*add_extra(in_channels, branches[1], conv_sz))) in_channels = 185
3 再然后,使用moduleList方法,把普通列表專成pytorch下的模塊
# to list self.conf_bra = nn.ModuleList(conf_bra_list) self.paf_bra = nn.ModuleList(paf_bra_list)
4 最后,調(diào)用就好了
out_0 = x # the base transform for k in range(len(self.vgg)): out_0 = self.vgg[k](out_0) # local name space name = locals() confs = [] pafs = [] outs = [] length = len(self.conf_bra) for i in range(length): name['conf_%s' % (i + 1)] = self.conf_bra[i](name['out_%s' % i]) name['paf_%s' % (i + 1)] = self.paf_bra[i](name['out_%s' % i]) name['out_%s' % (i + 1)] = torch.cat([name['conf_%s' % (i + 1)], name['paf_%s' % (i + 1)], out_0], 1) confs.append('conf_%s' % (i + 1)) pafs.append('paf_%s' % (i + 1)) outs.append('out_%s' % (i + 1))
5 順便裝了一下,使用了python局部變量命名空間,name = locals(),其實(shí)完全使用普通列表保存變量就好了,高興就好。
以上是“pytorch網(wǎng)絡(luò)層結(jié)構(gòu)數(shù)組化的示例分析”這篇文章的所有內(nèi)容,感謝各位的閱讀!希望分享的內(nèi)容對大家有幫助,更多相關(guān)知識,歡迎關(guān)注億速云行業(yè)資訊頻道!
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場,如果涉及侵權(quán)請聯(lián)系站長郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。