Questions tagged [snpe]
24 questions
0
votes
0 answers
SNPE multi batchSize inference
How do I modify a single batch to multiple batches? I am currently using Yolov3 for my work. I tried to modify it according to the sample but it didn't finish my work. Could anyone please tell me how to use the multi-batch…
OliverBerry
- 1
- 1
0
votes
0 answers
How to use UserBuffer in which encoding type is FLOAT from C++ API in Qualcomm
I have frame data in an unsigned char* array. I want to create UserBuffer of Qualcomm to use it in SNPE. How can I create the UserBuffer? I didn't find any resources on their platform. The example given in their SDK doesn't seem very helpful.
Can…
Kazi Sohan
- 11
- 2
0
votes
1 answer
SNPE - How can I predict on a model with two (or more) inputs?
I've built a Keras model with two inputs that I'd like to predict on with SNPE on my phone. I've already converted it successfully, it's just the C++ code that I'm having trouble with right now. I'm able to predict on a model with one input with any…
Shane Smiskol
- 952
- 1
- 11
- 38
0
votes
1 answer
Problem Converting Caffe model to dlc using SNPE
I am facing an issue in converting my caffe model to dlc using SNPE.
Specifically in the "Scale" layer.
The first two layers are as follows
name: "First"
input: "data"
input_shape {
dim: 1
dim: 3
dim: xxx
dim: xxx
}
layer {
name:…
Nithin G A
- 73
- 8
0
votes
1 answer
Snapdragon Neural Processing Engine (SNPE) and Tiny Yolo on Android App
for my final university exam I am trying to use SNPE with Tiny YOLO for real time object detection in an Android App. I succesfully converted model to DLC format, but i can't understand how to prepare input tensors and how to process output tensors.…
pado
- 123
- 1
- 11
0
votes
1 answer
ElementWise resolver must implement broadcast method - Qualcomm SNPE
Encountered a problem while trying to run the setup script from Qualcomm SNPE 1.14 to convert a MobileNet_V2 graph into .DLC format.
It passes the optimize_for_inference stage but fails when running convert_to_dlc receiving the following error:
-…
Thirsty4K
- 68
- 8
0
votes
1 answer
Qualcomm SNPE sdk and SSD model
I try to use Qualcomm SNPE to integrate optimize SSD model computation on my snapdragon 820. Il succefully transform the SSD Tensorflow model to the DLC file.
There is no example of integration of SSD model I try different solution but non succes.…
dev dev
- 109
- 15
0
votes
1 answer
how to download and convert a pre-trained "inception_v3" example in Tensorflow format:?
I am just starting to use tensor flow while downloading ML fileby using python API and I am getting the below error
"C:\Users\IVISSW\Desktop\snpe-1.12.0> python
./models/inception_v3/scripts/setup_inceptionv3.py -a
./temp-assets-cache -d …
ashish
- 307
- 4
- 15
0
votes
2 answers
convert tensorflow .pb to .dlc fail with snpe
I save the graph to a .pb file. I get an error when I convert the .pb to .dlc. Anyone know why?
My code to build the model:
import tensorflow as tf
from tensorflow.python.framework.graph_util import convert_variables_to_constants
from…
chenguoting
- 1
- 2