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 model can't work with any input size. I am trying to find a way that resizes input shapes of a DLC model without initializing model with "snpe-tensorflow-to-dlc --input_dims 1,512,512,3" because this way is consuming. Actually, I want to resize input shapes in dlc model. can anybody help me?
Is there any way to resize input shapes in SNPE (dlc)?
779 views Asked by ALiBahri At
1
There are 1 answers
Related Questions in TENSORFLOW
- (Tensorflow)Does the op assign change the gradient computation?
- Tensorflow Windows Accessing Folders Denied:"NewRandomAccessFile failed to Create/Open: Access is denied. ; Input/output error"
- Android App TensorFlow Google Cloud ML
- Convert Tensorflow model to Caffe model
- Google Tensorflow LSTMCell Variables Mapping to Hochreiter97_lstm.pdf paper
- additive Gaussian noise in Tensorflow
- TFlearn evaluate method results meaning
- Regularization losses Tensorflow - TRAINABLE_VARIABLES to Tensor Array
- feed picture to model tensorflow for training
- Fail to read the new format of tensorflow checkpoint?
Related Questions in DYNAMIC
- Convert Apache VirtualHost to nginx Server Block for Dynamic Subdomains
- Nested dynamically generated forms using jQuery
- AngularJS Dynamic Slider Control
- dynamic content control mapping for MS word c#
- get value from the dynamic create textbox
- Android : Unable to change width of dynamic button
- saving matlab file (.mat) with dynamic name
- MODx Create dynamic frontend page / display manager page without login
- Dynamic XML parsing, data storage, and forms in c#
- Cannot convert type 'Umbraco.Core.Dynamics.DynamicNull' to 'Umbraco.....' - Umbraco v6
Related Questions in RESIZE
- How to resize images with PHP PARSE SDK
- Problems with Clickable Divs in side bar
- Resizing images failing on start, setContentView & bitmap factory[android]
- HTML, CSS | Page Blurs on resize
- A view that can be moved and resized on android
- Creating a vertically draggable container in Adobe Flex 3.5
- Resize <iframe> so that whole content just scales down or up
- How to resize a flexible text-area on a mobile device?
- Why is my array of struct not resizing with Array.Resize?
- Resize image to the size of JLabel taken dynamically from file chooser in Swing app
Related Questions in SNPE
- Qualcomm Neural Processing Engine (NPE) loading model failed
- Implementing mobilenetssd with SNPE
- Snapdragon neural processing- SNPE
- Unable to load the frozen model (.pb) in GraphDef in tensorflow version 2.x
- Problem Converting Caffe model to dlc using SNPE
- Is there any way to resize input shapes in SNPE (dlc)?
- ElementWise resolver must implement broadcast method - Qualcomm SNPE
- Does Qualcomm SNPE work on a linux board?
- pb to dlc conversion with snpe fails using a re trained Tensorflow Object Detection model
- How to modify Sample Code 1.51 to run DLC with AIP mode like snpe-net-run?
Popular Questions
- How do I undo the most recent local commits in Git?
- How can I remove a specific item from an array in JavaScript?
- How do I delete a Git branch locally and remotely?
- Find all files containing a specific text (string) on Linux?
- How do I revert a Git repository to a previous commit?
- How do I create an HTML button that acts like a link?
- How do I check out a remote Git branch?
- How do I force "git pull" to overwrite local files?
- How do I list all files of a directory?
- How to check whether a string contains a substring in JavaScript?
- How do I redirect to another webpage?
- How can I iterate over rows in a Pandas DataFrame?
- How do I convert a String to an int in Java?
- Does Python have a string 'contains' substring method?
- How do I check if a string contains a specific word?
Popular Tags
Trending Questions
- UIImageView Frame Doesn't Reflect Constraints
- Is it possible to use adb commands to click on a view by finding its ID?
- How to create a new web character symbol recognizable by html/javascript?
- Why isn't my CSS3 animation smooth in Google Chrome (but very smooth on other browsers)?
- Heap Gives Page Fault
- Connect ffmpeg to Visual Studio 2008
- Both Object- and ValueAnimator jumps when Duration is set above API LvL 24
- How to avoid default initialization of objects in std::vector?
- second argument of the command line arguments in a format other than char** argv or char* argv[]
- How to improve efficiency of algorithm which generates next lexicographic permutation?
- Navigating to the another actvity app getting crash in android
- How to read the particular message format in android and store in sqlite database?
- Resetting inventory status after order is cancelled
- Efficiently compute powers of X in SSE/AVX
- Insert into an external database using ajax and php : POST 500 (Internal Server Error)
Usually deployment solutions work with fixed input shapes because they assume some widely acknowledged usage model - resize all picture of the same certain size and do inference. And due to this usage model, developers of deployment solutions do not prioritize model loading time while they usually prioritize the inference time. The same happens in SNPE, in OpenVINO, in TFLite, etc.
To illustrate the times, here is some results from Snapdragon 820. To load Inception v3 to CPU takes 715ms, to load model to DSP takes 3 seconds. Inference on CPU takes 1 sec, inference on DSP takes 100ms. You see that loading time on DSP is bigger than on CPU, but inference time is much much better.
At the same time, usually it is allowed to change a shape before loading of the model assuming that all input pictures will have different size (but again, same for all pictures) than shapes for which model was trained. For SNPE it is SNPEBuilder::setInputDimensions If model allow to do reshape and if no bugs in SNPE implementation, the model can be reshaped and loaded.
Not sure if your usage model fits to the vision described in the first paragraph. At the same time, to have a benefit from different input size you need to develop special topology that unlikely be supported by SNPE. If you take just regular SSD and reshape it to different size and measure accuracy on validation set, the most likely you get the best result on shpaes where model was trained.