matconvnet源代码:skipForward

最新推荐文章于 2022-11-24 18:18:29 发布

RtZero

最新推荐文章于 2022-11-24 18:18:29 发布

阅读量1k

点赞数

分类专栏： matconvnet

matconvnet 专栏收录该内容

5 篇文章

订阅专栏

本文详细解析了深度学习中各种网络层的实现方法，包括卷积层(conv)、转置卷积层(convt)、池化层(pool)、归一化层(normalize)、全连接层(softmax)等，并介绍了激活函数如ReLU和Sigmoid的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

 case 'conv'
      res(i+1).x = vl_nnconv(res(i).x, l.weights{1}, l.weights{2}, ...
        'pad', l.pad, ...
        'stride', l.stride, ...
        'dilate', l.dilate, ...
        l.opts{:}, ...
        cudnn{:}) ;

    case 'convt'
      res(i+1).x = vl_nnconvt(res(i).x, l.weights{1}, l.weights{2}, ...
        'crop', l.crop, ...
        'upsample', l.upsample, ...
        'numGroups', l.numGroups, ...
        l.opts{:}, ...
        cudnn{:}) ;

    case 'pool'
      res(i+1).x = vl_nnpool(res(i).x, l.pool, ...
        'pad', l.pad, 'stride', l.stride, ...
        'method', l.method, ...
        l.opts{:}, ...
        cudnn{:}) ;

    case {'normalize', 'lrn'}
      res(i+1).x = vl_nnnormalize(res(i).x, l.param) ;

    case 'softmax'
      res(i+1).x = vl_nnsoftmax(res(i).x) ;

    case 'loss'
      res(i+1).x = vl_nnloss(res(i).x, l.class) ;

    case 'softmaxloss'
      res(i+1).x = vl_nnsoftmaxloss(res(i).x, l.class) ;

    case 'relu'
      if l.leak > 0, leak = {'leak', l.leak} ; else leak = {} ; end
      res(i+1).x = vl_nnrelu(res(i).x,[],leak{:}) ;

    case 'sigmoid'
      res(i+1).x = vl_nnsigmoid(res(i).x) ;

    case 'noffset'
      res(i+1).x = vl_nnnoffset(res(i).x, l.param) ;

    case 'spnorm'
      res(i+1).x = vl_nnspnorm(res(i).x, l.param) ;

    case 'dropout'
      if testMode
        res(i+1).x = res(i).x ;
      else
        [res(i+1).x, res(i+1).aux] = vl_nndropout(res(i).x, 'rate', l.rate) ;
      end

    case 'bnorm'
      if testMode
        res(i+1).x = vl_nnbnorm(res(i).x, l.weights{1}, l.weights{2}, ...
                                'moments', l.weights{3}, ...
                                'epsilon', l.epsilon, ...
                                bnormCudnn{:}) ;
      else
        res(i+1).x = vl_nnbnorm(res(i).x, l.weights{1}, l.weights{2}, ...
                                'epsilon', l.epsilon, ...
                                bnormCudnn{:}) ;
      end

    case 'pdist'
      res(i+1).x = vl_nnpdist(res(i).x, l.class, l.p, ...
        'noRoot', l.noRoot, ...
        'epsilon', l.epsilon, ...
        'aggregate', l.aggregate, ...
        'instanceWeights', l.instanceWeights) ;

    case 'custom'
      res(i+1) = l.forward(l, res(i), res(i+1)) ;