TensorRT 3.0 can't handle average pooling layer with padding in NVcaffe's inception_v3 model

update:
the issue is not concat. it’s the padding params used in following pooling layer. remove the padding parameter works can pass this layer.

layer {
name: “3A/p4_pool”
type: “Pooling”
bottom: “conv6/bn”
top: “3A/p4_pool”
pooling_param {
pool: AVE
kernel_size: 3
pad: 1
}
}
input shape (1, 288, 35 ,35)
#################
run tensorrt with ngc docker 17.12.
model from NVCaffe’s inception_v3.

Issue
can’t handle the concat layer:
to reproduce:
giexec --deploy=deploy.prototxt --batch=1 --output=3A/concat
deploy: deploy.prototxt
batch: 1
output: 3A/concat
Input “data”: 3x299x299
Output “3A/concat”: 288x35x35
giexec: cudnnBuilder2.cpp:165: nvinfer1::builder::Format::Type nvinfer1::builder::supportedFormats(const nvinfer1::builder::Node&, nvinfer1::builder::Format::Type, const nvinfer1::cudnn::HardwareContext&): Assertion `result’ failed.
Aborted (core dumped)

Me too!!!!!
max pooling is ok, but the following avg pooling is crashed.
when the AVG pooling is substitued with MAX pooling, everything is ok!

cudnnBuilder2.cpp:165: nvinfer1::builder::Format::Type nvinfer1::builder::supportedFormats(const nvinfer1::builder::Node&, nvinfer1::builder::Format::Type, const nvinfer1::cudnn::HardwareContext&): Assertion `result’ failed.
Aborted (core dumped)

layer {
name: “pool2”
type: “Pooling”
bottom: “conv2_1_conat”
top: “pool2”
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
pad: 0
}
}

layer {
name: “inception_1_pool_2_1”
type: “Pooling”
bottom: “pool2”
top: “inception_1_pool_2_1”
pooling_param {
pool: AVE
kernel_size: 5
stride: 1
pad: 2
}
}