Part Number: TDA2EXEVM
This is the model I trained, and I ran into some problems on the PC.
name: "cifar_mod_BSM_deploy"
input: "data"
input_shape {
dim: 1
dim: 3
dim: 320
dim: 180
}
layer {
name: "data/bias"
type: "Bias"
bottom: "data"
top: "data/bias"
param {
lr_mult: 0
decay_mult: 0
}
bias_param {
filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data/bias"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
bias_term: true
pad: 1
kernel_size: 5
group: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
dilation: 1
}
}
layer {
name: "conv1/bn"
type: "BatchNorm"
bottom: "conv1"
top: "conv1"
batch_norm_param {
moving_average_fraction: 0.99
eps: 0.0001
}
}
layer {
name: "conv1/relu"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 18
bias_term: true
pad: 1
kernel_size: 5
group: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
dilation: 1
}
}
layer {
name: "conv2/bn"
type: "BatchNorm"
bottom: "conv2"
top: "conv2"
batch_norm_param {
moving_average_fraction: 0.99
eps: 0.0001
}
}
layer {
name: "conv2/relu"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
bias_term: true
pad: 1
kernel_size: 5
group: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
dilation: 1
}
}
layer {
name: "conv3/bn"
type: "BatchNorm"
bottom: "conv3"
top: "conv3"
batch_norm_param {
moving_average_fraction: 0.99
eps: 0.0001
}
}
layer {
name: "conv3/relu"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "pool3"
type: "Pooling"
bottom: "conv3"
top: "pool3"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv4"
type: "Convolution"
bottom: "pool3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 32
bias_term: true
pad: 1
kernel_size: 3
group: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
dilation: 1
}
}
layer {
name: "conv4/bn"
type: "BatchNorm"
bottom: "conv4"
top: "conv4"
batch_norm_param {
moving_average_fraction: 0.99
eps: 0.0001
}
}
layer {
name: "conv4/relu"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
bias_term: true
pad: 1
kernel_size: 5
group: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
dilation: 1
}
}
layer {
name: "conv5/bn"
type: "BatchNorm"
bottom: "conv5"
top: "conv5"
batch_norm_param {
moving_average_fraction: 0.99
eps: 0.0001
}
}
layer {
name: "conv5/relu"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "ip5"
type: "InnerProduct"
bottom: "pool5"
top: "ip5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prob"
type: "Softmax"
bottom: "ip5"
top: "prob"
}
cd "C:\PROCESSOR_SDK_VISION_03_02_00_00\ti_components\algorithms\REL.TIDL.01.00.00.00\modules\ti_dl\utils\tidlModelImport"
>tidl_model_import.out.exe ..\..\test\testvecs\config\import\tidl_import_jseg21.txt
the file "tidl_import_jseg21.txt" is :
# Default - 0
randParams = 0
# 0: Caffe, 1: TensorFlow, Default - 0
modelType = 0
# test sparse 0, dense 1
conv2dKernelType = 0
# 0: Fixed quantization By tarininng Framework, 1: Dyanamic quantization by TIDL, Default - 1
quantizationStyle = 1
# quantRoundAdd/100 will be added while rounding to integer, Default - 50
#quantRoundAdd = 25
quantRoundAdd = 25
#numParamBits = 8
numParamBits = 8
# 0 : 8bit Unsigned, 1 : 8bit Signed Default - 1
inElementType = 0
inputNetFile = "C:\PROCESSOR_SDK_VISION_03_02_00_00\ti_components\algorithms\REL.TIDL.01.00.00.00\modules\ti_dl\utils\tidlModelImport\cifar_mod_BSM_deploy.prototxt"
inputParamsFile = "C:\PROCESSOR_SDK_VISION_03_02_00_00\ti_components\algorithms\REL.TIDL.01.00.00.00\modules\ti_dl\utils\tidlModelImport\cifar_mod_BSM_iter_584.caffemodel"
outputNetFile = "..\..\test\testvecs\config\tidl_models\tidl_net_jsegnet21v2.bin"
outputParamsFile = "..\..\test\testvecs\config\tidl_models\tidl_param_jsegnet21v2.bin"
#preProcType = 3
rawSampleInData = 1
numSampleInData = 9
sampleInData = "..\..\test\testvecs\input\images_9.y"
#sampleInData = "..\..\test\testvecs\input\bird8.jpg"
tidlStatsTool = "..\quantStatsTool\eve_test_dl_algo.out.exe"
inWidth = 180
inHeight = 320
The output is:
199 190 254
201 192 254
201 192 254
201 192 254
199 190 254
199 190 254
199 190 254
199 190 254
199 190 254
Enter nine different pictures, and the results are basically the same.
Why is that?
