Deep learning caffe:无法更改池层的焊盘大小

Deep learning caffe:无法更改池层的焊盘大小,deep-learning,caffe,conv-neural-network,pycaffe,convolutional-neural-network,Deep Learning,Caffe,Conv Neural Network,Pycaffe,Convolutional Neural Network,更改pas大小时,我遇到此错误。我尝试了不同的焊盘尺寸,但我得到了类似的错误。详情如下: layer { name: "Pooling1" type: "Pooling" bottom: "Convolution2" top: "Pooling1" pooling_param { pool: MAX kernel_h: 1 kernel_w: 2 stride_h: 1 stride_w: 2 pad_h: 0

更改pas大小时,我遇到此错误。我尝试了不同的焊盘尺寸,但我得到了类似的错误。详情如下:

    layer {
  name: "Pooling1"
  type: "Pooling"
  bottom: "Convolution2"
  top: "Pooling1"
  pooling_param {
    pool: MAX
    kernel_h: 1
    kernel_w: 2
    stride_h: 1
    stride_w: 2
    pad_h: 0
    pad_w: 3
  }
这就是错误:

...
Creating layer Convolution2
I0525 10:45:37.403520 20575 net.cpp:84] Creating Layer Convolution2
I0525 10:45:37.403524 20575 net.cpp:406] Convolution2 <- Concat1
I0525 10:45:37.403529 20575 net.cpp:380] Convolution2 -> Convolution2
I0525 10:45:37.403555 20575 net.cpp:122] Setting up Convolution2
I0525 10:45:37.403560 20575 net.cpp:129] Top shape: 1 16 1 4076 (65216)
I0525 10:45:37.403563 20575 net.cpp:137] Memory required for data: 3022080
I0525 10:45:37.403568 20575 layer_factory.hpp:77] Creating layer Pooling1
I0525 10:45:37.403571 20575 net.cpp:84] Creating Layer Pooling1
I0525 10:45:37.403575 20575 net.cpp:406] Pooling1 <- Convolution2
I0525 10:45:37.403581 20575 net.cpp:380] Pooling1 -> Pooling1
F0525 10:45:37.403594 20575 pooling_layer.cpp:74] Check failed: pad_w_ < kernel_w_ (3 vs. 2)
。。。
创建层卷积2
I0525 10:45:37.403520 20575 net.cpp:84]创建层卷积2
I0525 10:45:37.403524 20575 net.cpp:406]卷积2卷积2
I0525 10:45:37.403555 20575 net.cpp:122]设置卷积2
I0525 10:45:37.403560 20575净。cpp:129]顶部形状:1 16 1 4076(65216)
I0525 10:45:37.403563 20575 net.cpp:137]数据所需的内存:3022080
I0525 10:45:37.403568 20575层\u工厂。hpp:77]创建层池1
I0525 10:45:37.403571 20575 net.cpp:84]创建层池1
I0525 10:45:37.403575 20575 net.cpp:406]poolg1 poolg1
F0525 10:45:37.403594 20575池化层。cpp:74]检查失败:填充

提前谢谢

从您收到的错误消息中可以清楚地看到问题:您将pad设置为大于池内核大小。缩小衬垫,你应该会没事的

那么我的上衣的尺寸正在改变,与下一层不兼容!我想要一件上衣:1x16x1x2044;但如果pad=1,则top:1x16x1x2038!那么如何增加顶部大小?@NimaHatami看看你可能想玩你的内核大小?@NimaHatami你的输入形状太小,无法得到你期望的输出形状。你想在这里实现什么?您可能需要填充一些其他层…我试图将此顶部(1x16x1x2038)与另一个尺寸为1x16x1x2044的顶部相加。我决定通过添加上一个conv层来实现这一点,它工作得很好!