Stack Overflow
Stack Overflow

Questions tagged [snpe]

24 questions
4
votes
1 answer

Qualcomm Neural Processing Engine (NPE) loading model failed

I follow Qualcomm Neural Processing Engine tutorial to build the sample app. When app loads model occur error. Error message following 09-01 12:21:20.600 30650-30681/com.qualcomm.qti.snpe.imageclassifiers E/LoadNetworkTask: Unable to create network!…
Elirex
  • 63
  • 1
  • 9
3
votes
3 answers

Qualcomm SNPE block the UI Thread

using the Qualcomm NeturalNetwork SDK. i can run the SNPE SDK Example and change to inception_v3 model, works fine. but snpe will block-ui thread in the execute(); i have no way to stop this. android user will get bad UX. i have tryed: low priority…
SomeOneNewbid
  • 55
  • 5
3
votes
2 answers

Neural network specified with tf.layers inserting undesired reshape operations

This simple neural network defined in python: input_layer = tf.placeholder(tf.float32, shape=[1, 1, 8000, 1], name='input_layer') # Convolutional Layer conv = tf.layers.conv2d( inputs=input_layer, filters=32, …
Mike Vella
  • 10,187
  • 14
  • 59
  • 86
3
votes
1 answer

Error when using SNPE to convert tensorflow dense layer

When converting a custom tensorflow graph I am seeing errors relating to the conversion of a dense layer from pb to DLC format: 2017-11-02 13:43:35,260 - 305 - WARNING - WARNING_TF_SCOPE_OP_NOT_CONSUMED: Operation (dense/Tensordot/transpose) not…
Mike Vella
  • 10,187
  • 14
  • 59
  • 86
2
votes
0 answers

Unable to load the frozen model (.pb) in GraphDef in tensorflow version 2.x

Created a simple dummy sequential model in tf.keras as shown below: model = tf.keras.Sequential() model.add(layers.Dense(10, input_shape=(100, 100))) model.add(layers.Conv1D(3, 2)) model.add(layers.Flatten()) model.add(layers.Dense(10,…
Arvind
  • 198
  • 2
  • 11
2
votes
0 answers

How to transform classify_image_graph_def.pb from "TF for poets" tutorial into inception_v3_2016_08_28_frozen.pb from Qualcomm SNPE tutorial

Does anybody know, how to transform classify_image_graph_def.pb from google's tensorflow for poets tutorial: https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0 into inception_v3_2016_08_28_frozen.pb utilised by Qualcomm in its…
Rafal
  • 479
  • 1
  • 4
  • 10
1
vote
1 answer

Snapdragon neural processing- SNPE

I am quite new to this platform so please be kind if my question is stupid. Currently I am trying to integrate a deep learning model by using SNPE to detect human pose. The architecture of the model is as following: Input -> CNN layers -> seperate…
phonix94
  • 15
  • 2
1
vote
1 answer

pb to dlc conversion with snpe fails using a re trained Tensorflow Object Detection model

Tensorflow version: 2.5 Snpe version: 1.51 Using a pre-trained model from the Tensorflow Model Zoo, I am re-training it to detect only one class of object. Exporting the trained model as saved_model format according to TF2. However, running this…
Amith Gowda
  • 11
  • 3
1
vote
1 answer

Is there any way to resize input shapes in SNPE (dlc)?

I have trained a model based on Tensorflow. This model is supposed to work on the mobile phone but I have got a problem when converting froze graph (pb) to deep learning container(dlc). I have to set the input size to be constant. This cause that…
ALiBahri
  • 11
  • 2
1
vote
1 answer

Why SNPE SDK is very Slow?

I tried example provided by Qualcomm…
Simran Marok
  • 707
  • 1
  • 5
  • 9
1
vote
1 answer

Does Qualcomm SNPE work on a linux board?

I wish to get the qualcomm SNPE (snapdragon neural processing engine) working on my linux (not Android) board (flightPro w/ qualcomm 820.) . It works fine on the cpu. I've successfully followed the examples provided to load alexnet onto my 820…
Peter Gaston
  • 176
  • 13
1
vote
0 answers

Implementing mobilenetssd with SNPE

I managed to transform the ssd_mobilenet_v1_coco_2017_11_17 model to a dlc file. The model ran on Android but the output is practically blank (only 1.0 for scores, 0.0 for boxes and classes) I'm not sure what exactly is wrong. float[]…
Billy Batson
  • 104
  • 2
  • 11
1
vote
2 answers

Retraining Inception v3 model without reshape layer

I had retrained inception v3 model for a custom dataset. But after retraining when i look at the TenosorGraph i found that a layer named as reshape followed by a fully connected layer is added. I have to run the model on an embedded device using…
Vishal Ghorpade
  • 135
  • 11
0
votes
0 answers

How to modify Sample Code 1.51 to run DLC with AIP mode like snpe-net-run?

SampleCode cannot run in AIP mode while snpe-net-run can run (snpe-1.51). The error message is: AIP runtime invalid parameter. Mismatch between network offline and online view. How could I change Sample Code a bit to be able to run my DLC with AIP…
WWW
  • 1
  • 2
0
votes
0 answers

AttributeError: module 'tvm.relay.op.image' has no attribute 'resize'

How to fix this problem? snpe-tflite-to-dlc --input_network MobileNetv2yolo_completeArch_305_test_loss=14.214842.ckpt-305.tflite --input_dim input "2,256,416,3" --output_path…
OliverBerry
  • 1
  • 1
1
2