I use TensorRT SDK 5.1 for CUDA10 to load a LightCNN caffe model(a cnn model for extracting person face features) on Windows10 Pro,but the call to builder::buildCudaEngine() failed, the logger report “Error: Unused Input: data”, what’s the meaning of the error?How to solve it?
below is the LightCNN model’s prototxt define:
name: “DeepFace_set003_net”
input: “data”
input_dim: 1
input_dim: 1
input_dim: 128
input_dim: 128
layers{
name: “conv1”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 5
stride: 1
pad: 2
weight_filler {
type: “xavier”
}
bias_filler {
type: “constant”
value: 0.1
}
}
bottom: “data”
top: “conv1”
}
layers{
name: “slice1”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv1”
top: “slice1_1”
top: “slice1_2”
}
layers{
name: “etlwise1”
type: ELTWISE
bottom: “slice1_1”
bottom: “slice1_2”
top: “eltwise1”
eltwise_param {
operation: MAX
}
}
layers{
name: “pool1”
type: POOLING
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
bottom: “eltwise1”
top: “pool1”
}
layers{
name: “conv2a”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 1
stride: 1
weight_filler {
type: “xavier”
}
bias_filler {
type: “constant”
value: 0.1
}
}
bottom: “pool1”
top: “conv2a”
}
layers{
name: “slice2a”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv2a”
top: “slice2a_1”
top: “slice2a_2”
}
layers{
name: “etlwise2a”
type: ELTWISE
bottom: “slice2a_1”
bottom: “slice2a_2”
top: “eltwise2a”
eltwise_param {
operation: MAX
}
}
layers{
name: “conv2”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 192
kernel_size: 3
stride: 1
pad: 1
weight_filler {
type: “xavier”
}
bias_filler {
type: “constant”
value: 0.1
}
}
bottom: “eltwise2a”
top: “conv2”
}
layers{
name: “slice2”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv2”
top: “slice2_1”
top: “slice2_2”
}
layers{
name: “etlwise2”
type: ELTWISE
bottom: “slice2_1”
bottom: “slice2_2”
top: “eltwise2”
eltwise_param {
operation: MAX
}
}
layers{
name: “pool2”
type: POOLING
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
bottom: “eltwise2”
top: “pool2”
}
layers{
name: “conv3a”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 192
kernel_size: 1
stride: 1
weight_filler {
type: “xavier”
}
bias_filler {
type: “constant”
value: 0.1
}
}
bottom: “pool2”
top: “conv3a”
}
layers{
name: “slice3a”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv3a”
top: “slice3a_1”
top: “slice3a_2”
}
layers{
name: “etlwise3a”
type: ELTWISE
bottom: “slice3a_1”
bottom: “slice3a_2”
top: “eltwise3a”
eltwise_param {
operation: MAX
}
}
layers{
name: “conv3”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
kernel_size: 3
stride: 1
pad: 1
weight_filler {
type: “xavier”
}
bias_filler {
type: “constant”
value: 0.1
}
}
bottom: “eltwise3a”
top: “conv3”
}
layers{
name: “slice3”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv3”
top: “slice3_1”
top: “slice3_2”
}
layers{
name: “etlwise3”
type: ELTWISE
bottom: “slice3_1”
bottom: “slice3_2”
top: “eltwise3”
eltwise_param {
operation: MAX
}
}
layers{
name: “pool3”
type: POOLING
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
bottom: “eltwise3”
top: “pool3”
}
layers{
name: “conv4a”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param{
num_output: 384
kernel_size: 1
stride: 1
weight_filler{
type:“xavier”
}
bias_filler{
type: “constant”
value: 0.1
}
}
bottom: “pool3”
top: “conv4a”
}
layers{
name: “slice4a”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv4a”
top: “slice4a_1”
top: “slice4a_2”
}
layers{
name: “etlwise4a”
type: ELTWISE
bottom: “slice4a_1”
bottom: “slice4a_2”
top: “eltwise4a”
eltwise_param {
operation: MAX
}
}
layers{
name: “conv4”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param{
num_output: 256
kernel_size: 3
stride: 1
pad: 1
weight_filler{
type:“xavier”
}
bias_filler{
type: “constant”
value: 0.1
}
}
bottom: “eltwise4a”
top: “conv4”
}
layers{
name: “slice4”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv4”
top: “slice4_1”
top: “slice4_2”
}
layers{
name: “etlwise4”
type: ELTWISE
bottom: “slice4_1”
bottom: “slice4_2”
top: “eltwise4”
eltwise_param {
operation: MAX
}
}
layers{
name: “conv5a”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param{
num_output: 256
kernel_size: 1
stride: 1
weight_filler{
type:“xavier”
}
bias_filler{
type: “constant”
value: 0.1
}
}
bottom: “eltwise4”
top: “conv5a”
}
layers{
name: “slice5a”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv5a”
top: “slice5a_1”
top: “slice5a_2”
}
layers{
name: “etlwise5a”
type: ELTWISE
bottom: “slice5a_1”
bottom: “slice5a_2”
top: “eltwise5a”
eltwise_param {
operation: MAX
}
}
layers{
name: “conv5”
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param{
num_output: 256
kernel_size: 3
stride: 1
pad: 1
weight_filler{
type:“xavier”
}
bias_filler{
type: “constant”
value: 0.1
}
}
bottom: “eltwise5a”
top: “conv5”
}
layers{
name: “slice5”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “conv5”
top: “slice5_1”
top: “slice5_2”
}
layers{
name: “etlwise5”
type: ELTWISE
bottom: “slice5_1”
bottom: “slice5_2”
top: “eltwise5”
eltwise_param {
operation: MAX
}
}
layers{
name: “pool4”
type: POOLING
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
bottom: “eltwise5”
top: “pool4”
}
layers{
name: “fc1”
type: INNER_PRODUCT
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 512
weight_filler {
type: “xavier”
}
bias_filler {
type: “constant”
value: 0.1
}
}
bottom: “pool4”
top: “fc1”
}
layers{
name: “slice_fc1”
type:SLICE
slice_param {
slice_dim: 1
}
bottom: “fc1”
top: “slice_fc1_1”
top: “slice_fc1_2”
}
layers{
name: “etlwise_fc1”
type: ELTWISE
bottom: “slice_fc1_1”
bottom: “slice_fc1_2”
top: “eltwise_fc1”
eltwise_param {
operation: MAX
}
}
layers{
name: “drop1”
type: DROPOUT
dropout_param{
dropout_ratio: 0.75
}
bottom: “eltwise_fc1”
top: “eltwise_fc1”
}
layers{
name: “fc2”
type: INNER_PRODUCT
inner_product_param{
num_output: 10575
weight_filler {
type: “xavier”
}
bias_filler {
type: “constant”
value: 0.1
}
}
bottom: “eltwise_fc1”
top: “fc2”
}
layers {
name: “softmax”
type: SOFTMAX
bottom: “fc2”
top: “prob”
include: { phase: TEST }
}