# Concat Layer ERROR

**URL:** <https://forums.developer.nvidia.com/t/concat-layer-error/69245>\
**Category:** TensorRT\
**Created:** [January 10, 2019, 2:55am UTC](https://forums.developer.nvidia.com/t/concat-layer-error/69245 "2019-01-10T02:55:02Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![Uestc\_vigor](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Uestc\_vigor](https://forums.developer.nvidia.com/u/Uestc_vigor)\
**Post date:** [January 10, 2019, 2:55am UTC](https://forums.developer.nvidia.com/t/concat-layer-error/69245/1 "2019-01-10T02:55:02Z")

</div>

solved

---

<div class="post-metadata">

**Author:** ![NVES](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nves/32/14043_2.png) [@NVES](https://forums.developer.nvidia.com/u/NVES)\
**Post date:** [January 10, 2019, 6:06pm UTC](https://forums.developer.nvidia.com/t/concat-layer-error/69245/2 "2019-01-10T18:06:21Z")

</div>

we are reviewing now and will keep you updated.

---

<div class="post-metadata">

**Author:** ![NVES](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nves/32/14043_2.png) [@NVES](https://forums.developer.nvidia.com/u/NVES)\
**Post date:** [January 10, 2019, 6:07pm UTC](https://forums.developer.nvidia.com/t/concat-layer-error/69245/3 "2019-01-10T18:07:46Z")

</div>

can you share the full runtime output?

---

<div class="post-metadata">

**Author:** ![Uestc\_vigor](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Uestc\_vigor](https://forums.developer.nvidia.com/u/Uestc_vigor)\
**Post date:** [January 13, 2019, 12:49pm UTC](https://forums.developer.nvidia.com/t/concat-layer-error/69245/4 "2019-01-13T12:49:28Z")

</div>

Sorry for the late update. Below is the runtime output. The model could run in caffe correctly.

####### input args#######  
C=3;H=608;W=608;caffemodel=./mobilenet\_deconv\_maxpool.caffemodel;calib=;class=1;mode=fp32;outputs=conv25,conv26,conv27;prototxt=./mobilenet\_deconv\_maxpool.prototxt;  
init plugin proto: ./mobilenet\_deconv\_maxpool.prototxt caffemodel: ./mobilenet\_deconv\_maxpool.caffemodel  
Begin parsing model…  
Input:1024 13 13  
ouputDims:1024 26 26  
ERROR: conv17/sum: all concat input tensors must have the same dimensions except on the concatenation axis  
run3: helpers.cpp:56: nvinfer1::DimsCHW nvinfer1::getCHW(const nvinfer1::Dims&): Assertion `d.nbDims \>= 3’ failed.  
Aborted (core dumped)

---

<div class="post-metadata">

**Author:** ![Uestc\_vigor](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Uestc\_vigor](https://forums.developer.nvidia.com/u/Uestc_vigor)\
**Post date:** [January 13, 2019, 12:52pm UTC](https://forums.developer.nvidia.com/t/concat-layer-error/69245/5 "2019-01-13T12:52:49Z")

</div>

I have tried to remove the maxpooling layer and connect the upsample layer with the conv15\_e/dw(modified the param in upsample layer to make sure the output width and height same with conv17), it works fine(without consider the weights, only prototxt). So the problem may caused by the maxpooling layer I guess.

---

<div class="post-metadata">

**Author:** ![NVES](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nves/32/14043_2.png) [@NVES](https://forums.developer.nvidia.com/u/NVES)\
**Post date:** [January 17, 2019, 1:16am UTC](https://forums.developer.nvidia.com/t/concat-layer-error/69245/6 "2019-01-17T01:16:47Z")

</div>

Hello,

to help us debug, can you share a small repro containing the parsing code and model that demonstrate the error you are seeing? You can DM me the files.
