# Problem Deploy trained model from DIGITS

**URL:** <https://forums.developer.nvidia.com/t/problem-deploy-trained-model-from-digits/67105>\
**Category:** Jetson TX2\
**Created:** [November 8, 2018, 12:08am UTC](https://forums.developer.nvidia.com/t/problem-deploy-trained-model-from-digits/67105 "2018-11-08T00:08:42Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![normanmk6ca](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@normanmk6ca](https://forums.developer.nvidia.com/u/normanmk6ca)\
**Post date:** [November 8, 2018, 12:08am UTC](https://forums.developer.nvidia.com/t/problem-deploy-trained-model-from-digits/67105/1 "2018-11-08T00:08:42Z")

</div>

So I have recently trained a model through DIGITS, and downloaded the model to Jetson TX2. I have also installed caffe on Jetson TX2. However, when I try to deploy the model. An error showed up:

I1107 23:19:12.893411 25303 net.cpp:257] Network initialization done.  
I1107 23:19:13.149886 25303 net.cpp:746] Ignoring source layer train-data  
F1107 23:19:13.149960 25303 blob.cpp:496] Check failed: count\_ == proto.data\_size() (34848 vs. 0)  
\*\*\* Check failure stack trace: \*\*\*  
Aborted (core dumped)

According to some research, this might be caused by version of deploy.prototxt file, which means the model was trained on one version of caffe while the Jetson tx2 is running another version. Someone mentioned prototxt file 1.0 has same problem running on 1.1 version. Any way I can transfer between these two version? Or am I missing something for setting? Please let me know, thank you so much!

Here is my prototxt file:  
input: “data”  
input\_shape {  
dim: 1  
dim: 3  
dim: 227  
dim: 227  
}  
layer {  
name: “conv1”  
type: “Convolution”  
bottom: “data”  
top: “conv1”  
param {  
lr\_mult: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
convolution\_param {  
num\_output: 96  
kernel\_size: 11  
stride: 4  
weight\_filler {  
type: “gaussian”  
std: 0.00999999977648  
}  
bias\_filler {  
type: “constant”  
value: 0.0  
}  
}  
}  
layer {  
name: “relu1”  
type: “ReLU”  
bottom: “conv1”  
top: “conv1”  
}  
layer {  
name: “norm1”  
type: “LRN”  
bottom: “conv1”  
top: “norm1”  
lrn\_param {  
local\_size: 5  
alpha: 9.99999974738e-05  
beta: 0.75  
}  
}  
layer {  
name: “pool1”  
type: “Pooling”  
bottom: “norm1”  
top: “pool1”  
pooling\_param {  
pool: MAX  
kernel\_size: 3  
stride: 2  
}  
}  
layer {  
name: “conv2”  
type: “Convolution”  
bottom: “pool1”  
top: “conv2”  
param {  
lr\_mult: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
convolution\_param {  
num\_output: 256  
pad: 2  
kernel\_size: 5  
group: 2  
weight\_filler {  
type: “gaussian”  
std: 0.00999999977648  
}  
bias\_filler {  
type: “constant”  
value: 0.10000000149  
}  
}  
}  
layer {  
name: “relu2”  
type: “ReLU”  
bottom: “conv2”  
top: “conv2”  
}  
layer {  
name: “norm2”  
type: “LRN”  
bottom: “conv2”  
top: “norm2”  
lrn\_param {  
local\_size: 5  
alpha: 9.99999974738e-05  
beta: 0.75  
}  
}  
layer {  
name: “pool2”  
type: “Pooling”  
bottom: “norm2”  
top: “pool2”  
pooling\_param {  
pool: MAX  
kernel\_size: 3  
stride: 2  
}  
}  
layer {  
name: “conv3”  
type: “Convolution”  
bottom: “pool2”  
top: “conv3”  
param {  
lr\_mult: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
convolution\_param {  
num\_output: 384  
pad: 1  
kernel\_size: 3  
weight\_filler {  
type: “gaussian”  
std: 0.00999999977648  
}  
bias\_filler {  
type: “constant”  
value: 0.0  
}  
}  
}  
layer {  
name: “relu3”  
type: “ReLU”  
bottom: “conv3”  
top: “conv3”  
}  
layer {  
name: “conv4”  
type: “Convolution”  
bottom: “conv3”  
top: “conv4”  
param {  
lr\_mult: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
convolution\_param {  
num\_output: 384  
pad: 1  
kernel\_size: 3  
group: 2  
weight\_filler {  
type: “gaussian”  
std: 0.00999999977648  
}  
bias\_filler {  
type: “constant”  
value: 0.10000000149  
}  
}  
}  
layer {  
name: “relu4”  
type: “ReLU”  
bottom: “conv4”  
top: “conv4”  
}  
layer {  
name: “conv5”  
type: “Convolution”  
bottom: “conv4”  
top: “conv5”  
param {  
lr\_mult: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
convolution\_param {  
num\_output: 256  
pad: 1  
kernel\_size: 3  
group: 2  
weight\_filler {  
type: “gaussian”  
std: 0.00999999977648  
}  
bias\_filler {  
type: “constant”  
value: 0.10000000149  
}  
}  
}  
layer {  
name: “relu5”  
type: “ReLU”  
bottom: “conv5”  
top: “conv5”  
}  
layer {  
name: “pool5”  
type: “Pooling”  
bottom: “conv5”  
top: “pool5”  
pooling\_param {  
pool: MAX  
kernel\_size: 3  
stride: 2  
}  
}  
layer {  
name: “fc6”  
type: “InnerProduct”  
bottom: “pool5”  
top: “fc6”  
param {  
lr\_mult: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
inner\_product\_param {  
num\_output: 4096  
weight\_filler {  
type: “gaussian”  
std: 0.00499999988824  
}  
bias\_filler {  
type: “constant”  
value: 0.10000000149  
}  
}  
}  
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: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
inner\_product\_param {  
num\_output: 4096  
weight\_filler {  
type: “gaussian”  
std: 0.00499999988824  
}  
bias\_filler {  
type: “constant”  
value: 0.10000000149  
}  
}  
}  
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: “fc8”  
type: “InnerProduct”  
bottom: “fc7”  
top: “fc8”  
param {  
lr\_mult: 1.0  
decay\_mult: 1.0  
}  
param {  
lr\_mult: 2.0  
decay\_mult: 0.0  
}  
inner\_product\_param {  
num\_output: 2  
weight\_filler {  
type: “gaussian”  
std: 0.00999999977648  
}  
bias\_filler {  
type: “constant”  
value: 0.0  
}  
}  
}  
layer {  
name: “softmax”  
type: “Softmax”  
bottom: “fc8”  
top: “softmax”  
}

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [November 8, 2018, 6:18am UTC](https://forums.developer.nvidia.com/t/problem-deploy-trained-model-from-digits/67105/2 "2018-11-08T06:18:25Z")

</div>

Hi,

DIGITs use the nvcaffe-0.15, do you use the same source?

Suppose DIGITs will give you a prototxt named as ‘deploy.prototxt’ when downloading the snapshot.  
Do you use it for launching on TX2?

By the way, it’s recommended to use TensorRT for better performance.  
You can find a tutorial here: [url][https://github.com/dusty-nv/jetson-inference[/url]](https://github.com/dusty-nv/jetson-inference%5B/url%5D)

Thanks.

---

<div class="post-metadata">

**Author:** ![normanmk6ca](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@normanmk6ca](https://forums.developer.nvidia.com/u/normanmk6ca)\
**Post date:** [November 8, 2018, 4:44pm UTC](https://forums.developer.nvidia.com/t/problem-deploy-trained-model-from-digits/67105/3 "2018-11-08T16:44:24Z")

</div>

> [@AastaLLL](#):
>
> Hi,
> 
> DIGITs use the _nvcaffe-0.15_, do you use the same source?
> 
> Suppose DIGITs will give you a prototxt named as ‘_deploy.prototxt_’ when downloading the snapshot.  
> Do you use it for launching on TX2?
> 
> By the way, it’s recommended to use TensorRT for better performance.  
> You can find a tutorial here: [https://github.com/dusty-nv/jetson-inference](https://github.com/dusty-nv/jetson-inference)
> 
> Thanks.

Hi,

Thank you so much for the reply, the tutorial link you provide is great!

I think the caffe I build on tx2 is just a normal version from here: [GitHub - jetsonhacks/installCaffeJTX2: Install Caffe on the NVIDIA Jetson TX2 Development Kit](https://github.com/jetsonhacks/installCaffeJTX2)  
However, I found nvcaffe for tx2 here: [NVCaffe support on TX2 - Jetson TX2 - NVIDIA Developer Forums](https://devtalk.nvidia.com/default/topic/1021931/jetson-tx2/nvcaffe-support-on-tx2/)

And thanks for the suggestion for using TensorRT, since I’m new to this platform and DIGITS, just trying to play around the try out everything.

Thanks again!

---

<div class="post-metadata">

**Author:** ![nadeemm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nadeemm/32/367020_2.png) [@nadeemm](https://forums.developer.nvidia.com/u/nadeemm)\
**Post date:** [October 18, 2021, 6:30pm UTC](https://forums.developer.nvidia.com/t/problem-deploy-trained-model-from-digits/67105/4 "2021-10-18T18:30:45Z")

</div>

Closed on October 18, 2021, 6:30pm UTC


