Check failed: K_ == new_K (6656 vs. 4096) Input size incompatible with inner product parameters












0















There is another similar question here. But that is not duplicate to my question as they are more on input dimension mismatch from network's requirement.



For me is I use customized network but input dimension is still the same.
I am not using any per-trained network as it is my own network.



I have problem with training on customized network with py-faster-rcnn method.
The original VGG16 NET has the following RCNN network.



layer {
name: "roi_pool5"
type: "ROIPooling"
bottom: "conv5_3"
bottom: "rois"
top: "pool5"
roi_pooling_param {
pooled_w: 7
pooled_h: 7
spatial_scale: 0.0625 # 1/16
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 16
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss_cls"
type: "SoftmaxWithLoss"
bottom: "cls_score"
bottom: "labels"
propagate_down: 1
propagate_down: 0
top: "loss_cls"
loss_weight: 1
}
layer {
name: "loss_bbox"
type: "SmoothL1Loss"
bottom: "bbox_pred"
bottom: "bbox_targets"
bottom: "bbox_inside_weights"
bottom: "bbox_outside_weights"
top: "loss_bbox"
loss_weight: 1
}


Which has roi_pool5 fed into inner product layer with output channels 4096.
roi_pool5 has input conv5_3 with 512 channels.



For me, my RCNN network has Inception layers with 64 channels. Then fed to innerproduct layer with output 512 channels.



According to discussion here, innerproduct layer is designed to accept fixed size of input. What does it mean to fixed size of input?



Where should I check to meet innerproduct layer's fixed size requirement?
My RCNN network is shown here.










share|improve this question





























    0















    There is another similar question here. But that is not duplicate to my question as they are more on input dimension mismatch from network's requirement.



    For me is I use customized network but input dimension is still the same.
    I am not using any per-trained network as it is my own network.



    I have problem with training on customized network with py-faster-rcnn method.
    The original VGG16 NET has the following RCNN network.



    layer {
    name: "roi_pool5"
    type: "ROIPooling"
    bottom: "conv5_3"
    bottom: "rois"
    top: "pool5"
    roi_pooling_param {
    pooled_w: 7
    pooled_h: 7
    spatial_scale: 0.0625 # 1/16
    }
    }
    layer {
    name: "fc6"
    type: "InnerProduct"
    bottom: "pool5"
    top: "fc6"
    param {
    lr_mult: 1
    }
    param {
    lr_mult: 2
    }
    inner_product_param {
    num_output: 4096
    }
    }
    layer {
    name: "relu6"
    type: "ReLU"
    bottom: "fc6"
    top: "fc6"
    }
    layer {
    name: "drop6"
    type: "Dropout"
    bottom: "fc6"
    top: "fc6"
    dropout_param {
    dropout_ratio: 0.5
    }
    }
    layer {
    name: "fc7"
    type: "InnerProduct"
    bottom: "fc6"
    top: "fc7"
    param {
    lr_mult: 1
    }
    param {
    lr_mult: 2
    }
    inner_product_param {
    num_output: 4096
    }
    }
    layer {
    name: "relu7"
    type: "ReLU"
    bottom: "fc7"
    top: "fc7"
    }
    layer {
    name: "drop7"
    type: "Dropout"
    bottom: "fc7"
    top: "fc7"
    dropout_param {
    dropout_ratio: 0.5
    }
    }
    layer {
    name: "cls_score"
    type: "InnerProduct"
    bottom: "fc7"
    top: "cls_score"
    param {
    lr_mult: 1
    }
    param {
    lr_mult: 2
    }
    inner_product_param {
    num_output: 4
    weight_filler {
    type: "gaussian"
    std: 0.01
    }
    bias_filler {
    type: "constant"
    value: 0
    }
    }
    }
    layer {
    name: "bbox_pred"
    type: "InnerProduct"
    bottom: "fc7"
    top: "bbox_pred"
    param {
    lr_mult: 1
    }
    param {
    lr_mult: 2
    }
    inner_product_param {
    num_output: 16
    weight_filler {
    type: "gaussian"
    std: 0.001
    }
    bias_filler {
    type: "constant"
    value: 0
    }
    }
    }
    layer {
    name: "loss_cls"
    type: "SoftmaxWithLoss"
    bottom: "cls_score"
    bottom: "labels"
    propagate_down: 1
    propagate_down: 0
    top: "loss_cls"
    loss_weight: 1
    }
    layer {
    name: "loss_bbox"
    type: "SmoothL1Loss"
    bottom: "bbox_pred"
    bottom: "bbox_targets"
    bottom: "bbox_inside_weights"
    bottom: "bbox_outside_weights"
    top: "loss_bbox"
    loss_weight: 1
    }


    Which has roi_pool5 fed into inner product layer with output channels 4096.
    roi_pool5 has input conv5_3 with 512 channels.



    For me, my RCNN network has Inception layers with 64 channels. Then fed to innerproduct layer with output 512 channels.



    According to discussion here, innerproduct layer is designed to accept fixed size of input. What does it mean to fixed size of input?



    Where should I check to meet innerproduct layer's fixed size requirement?
    My RCNN network is shown here.










    share|improve this question



























      0












      0








      0








      There is another similar question here. But that is not duplicate to my question as they are more on input dimension mismatch from network's requirement.



      For me is I use customized network but input dimension is still the same.
      I am not using any per-trained network as it is my own network.



      I have problem with training on customized network with py-faster-rcnn method.
      The original VGG16 NET has the following RCNN network.



      layer {
      name: "roi_pool5"
      type: "ROIPooling"
      bottom: "conv5_3"
      bottom: "rois"
      top: "pool5"
      roi_pooling_param {
      pooled_w: 7
      pooled_h: 7
      spatial_scale: 0.0625 # 1/16
      }
      }
      layer {
      name: "fc6"
      type: "InnerProduct"
      bottom: "pool5"
      top: "fc6"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 4096
      }
      }
      layer {
      name: "relu6"
      type: "ReLU"
      bottom: "fc6"
      top: "fc6"
      }
      layer {
      name: "drop6"
      type: "Dropout"
      bottom: "fc6"
      top: "fc6"
      dropout_param {
      dropout_ratio: 0.5
      }
      }
      layer {
      name: "fc7"
      type: "InnerProduct"
      bottom: "fc6"
      top: "fc7"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 4096
      }
      }
      layer {
      name: "relu7"
      type: "ReLU"
      bottom: "fc7"
      top: "fc7"
      }
      layer {
      name: "drop7"
      type: "Dropout"
      bottom: "fc7"
      top: "fc7"
      dropout_param {
      dropout_ratio: 0.5
      }
      }
      layer {
      name: "cls_score"
      type: "InnerProduct"
      bottom: "fc7"
      top: "cls_score"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 4
      weight_filler {
      type: "gaussian"
      std: 0.01
      }
      bias_filler {
      type: "constant"
      value: 0
      }
      }
      }
      layer {
      name: "bbox_pred"
      type: "InnerProduct"
      bottom: "fc7"
      top: "bbox_pred"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 16
      weight_filler {
      type: "gaussian"
      std: 0.001
      }
      bias_filler {
      type: "constant"
      value: 0
      }
      }
      }
      layer {
      name: "loss_cls"
      type: "SoftmaxWithLoss"
      bottom: "cls_score"
      bottom: "labels"
      propagate_down: 1
      propagate_down: 0
      top: "loss_cls"
      loss_weight: 1
      }
      layer {
      name: "loss_bbox"
      type: "SmoothL1Loss"
      bottom: "bbox_pred"
      bottom: "bbox_targets"
      bottom: "bbox_inside_weights"
      bottom: "bbox_outside_weights"
      top: "loss_bbox"
      loss_weight: 1
      }


      Which has roi_pool5 fed into inner product layer with output channels 4096.
      roi_pool5 has input conv5_3 with 512 channels.



      For me, my RCNN network has Inception layers with 64 channels. Then fed to innerproduct layer with output 512 channels.



      According to discussion here, innerproduct layer is designed to accept fixed size of input. What does it mean to fixed size of input?



      Where should I check to meet innerproduct layer's fixed size requirement?
      My RCNN network is shown here.










      share|improve this question
















      There is another similar question here. But that is not duplicate to my question as they are more on input dimension mismatch from network's requirement.



      For me is I use customized network but input dimension is still the same.
      I am not using any per-trained network as it is my own network.



      I have problem with training on customized network with py-faster-rcnn method.
      The original VGG16 NET has the following RCNN network.



      layer {
      name: "roi_pool5"
      type: "ROIPooling"
      bottom: "conv5_3"
      bottom: "rois"
      top: "pool5"
      roi_pooling_param {
      pooled_w: 7
      pooled_h: 7
      spatial_scale: 0.0625 # 1/16
      }
      }
      layer {
      name: "fc6"
      type: "InnerProduct"
      bottom: "pool5"
      top: "fc6"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 4096
      }
      }
      layer {
      name: "relu6"
      type: "ReLU"
      bottom: "fc6"
      top: "fc6"
      }
      layer {
      name: "drop6"
      type: "Dropout"
      bottom: "fc6"
      top: "fc6"
      dropout_param {
      dropout_ratio: 0.5
      }
      }
      layer {
      name: "fc7"
      type: "InnerProduct"
      bottom: "fc6"
      top: "fc7"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 4096
      }
      }
      layer {
      name: "relu7"
      type: "ReLU"
      bottom: "fc7"
      top: "fc7"
      }
      layer {
      name: "drop7"
      type: "Dropout"
      bottom: "fc7"
      top: "fc7"
      dropout_param {
      dropout_ratio: 0.5
      }
      }
      layer {
      name: "cls_score"
      type: "InnerProduct"
      bottom: "fc7"
      top: "cls_score"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 4
      weight_filler {
      type: "gaussian"
      std: 0.01
      }
      bias_filler {
      type: "constant"
      value: 0
      }
      }
      }
      layer {
      name: "bbox_pred"
      type: "InnerProduct"
      bottom: "fc7"
      top: "bbox_pred"
      param {
      lr_mult: 1
      }
      param {
      lr_mult: 2
      }
      inner_product_param {
      num_output: 16
      weight_filler {
      type: "gaussian"
      std: 0.001
      }
      bias_filler {
      type: "constant"
      value: 0
      }
      }
      }
      layer {
      name: "loss_cls"
      type: "SoftmaxWithLoss"
      bottom: "cls_score"
      bottom: "labels"
      propagate_down: 1
      propagate_down: 0
      top: "loss_cls"
      loss_weight: 1
      }
      layer {
      name: "loss_bbox"
      type: "SmoothL1Loss"
      bottom: "bbox_pred"
      bottom: "bbox_targets"
      bottom: "bbox_inside_weights"
      bottom: "bbox_outside_weights"
      top: "loss_bbox"
      loss_weight: 1
      }


      Which has roi_pool5 fed into inner product layer with output channels 4096.
      roi_pool5 has input conv5_3 with 512 channels.



      For me, my RCNN network has Inception layers with 64 channels. Then fed to innerproduct layer with output 512 channels.



      According to discussion here, innerproduct layer is designed to accept fixed size of input. What does it mean to fixed size of input?



      Where should I check to meet innerproduct layer's fixed size requirement?
      My RCNN network is shown here.







      tensorflow deep-learning caffe






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited Nov 22 '18 at 6:10







      batuman

















      asked Nov 22 '18 at 6:02









      batumanbatuman

      2,585744111




      2,585744111
























          0






          active

          oldest

          votes












          Your Answer






          StackExchange.ifUsing("editor", function () {
          StackExchange.using("externalEditor", function () {
          StackExchange.using("snippets", function () {
          StackExchange.snippets.init();
          });
          });
          }, "code-snippets");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "1"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53424755%2fcheck-failed-k-new-k-6656-vs-4096-input-size-incompatible-with-inner-pro%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Stack Overflow!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53424755%2fcheck-failed-k-new-k-6656-vs-4096-input-size-incompatible-with-inner-pro%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          How to change which sound is reproduced for terminal bell?

          Can I use Tabulator js library in my java Spring + Thymeleaf project?

          Title Spacing in Bjornstrup Chapter, Removing Chapter Number From Contents