image_classification | Strong Baseline with Many Tricks | Machine Learning library

I'm trying to convert an image classification dataset for use with Cloud TPU (as seen here) and in the examples that they give, there is this file (https://github.com/tensorflow/tpu/blob/master/tools/data_converter/image_classification/image_classification_data.py). Line 44 there is this import:

I use tensorflow models to train my dataset, running

My objective is to train a very simple CNN on MNIST using Tensorflow, convert it to TensorRT, and use it to perform inference on the MNIST test set using TensorRT, all on a Jetson Nano, but I am getting several errors and warnings, including “OutOfMemory Error in GpuMemory: 0”. To try and reduce memory footprint, I tried also creating a script where I simply load the TensorRT model (that had already been converted and saved in the previous script) and use it to perform inference on a small subset of the MNIST test set (100 floating point values), but I am still getting the same out of memory error. The entire directory containing the TensorRT model is only 488 KB, and the 100 test points can’t be taking up very much memory, so I am confused about why GPU memory is running out. What could be the reason for this, and how can I solve it?

Another thing which seems suspicious is that some of the Tensorflow logging info messages are being printed multiple times, EG “Successfully opened dynamic library libcudart”, “Successfully opened dynamic library libcublas”, “ARM64 does not support NUMA - returning NUMA node zero”. What could be the reason for this (EG dynamic libraries being opened over and over again), and could this have something to do with why the GPU memory keeps running out?

Shown below are the 2 Python scripts; the console output from each one is too long to post on Stack Overflow, but they can be seen attached to this Gist: https://gist.github.com/jakelevi1996/8a86f2c2257001afc939343891ee5de7

I'm new to tensorflow and was trying to follow the tutorial here https://cloud.google.com/tpu/docs/quickstart to run the MNIST TPU model.

I got error from

I'm able to run the TensorFlow lite image classification example on my mobile device. However, I want to exchange the image classification model to a pose recognition model. In my case, the output should consist of a list of (x,y) coordinates.

The respective line in the code looks like this:

The autokeras tutorial here https://colab.research.google.com/github/keras-team/autokeras/blob/master/docs/templates/tutorial/image_classification.ipynb

fails on the line:

I'm developing an app based on a sample of this repo (https://github.com/tensorflow/examples/blob/master/lite/examples/image_classification/ios/ImageClassification/Camera%20Feed/CameraFeedManager.swift). I have built the same structure for getting preview camera as the sample, so I start App on portrait mode and preview camera work correctly. But, I change to landscapeRigh or I set to app as only mode the landscaperight and.... preview is rotated 90º. I have tried to use the command: videoDataOutput.connection(with: .video)?.videoOrientation = .landscapeRight But it doesn't work… I can set all modes and it always has the same behaviour. Could you give me some advice to fix this problem? Thank you

The project I try to build:
https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/android

The configuration of my Android studio:
Project SDK: Android API 29 (Java version 1.8.0_202)
Project language level: 8
Project compiler output: set
No extra libraries
Nothing under the Problems tab in Project Structure

The error itself is the following:

Environment :

• OS : Win10 64bits
• Qt: 5.12.3
• NDK: r18b
• JDK: jdk1.8.0_201

I would like to use the tensorflow-lite with Qt5, but there are lots of issues when I try to import the java classes. But how could I download the tensorflow-lite-gpu, tensorflow-lite-cpu and tensorflow-lite-support?

The android studio make this work with 3 lines in the build.gradle, I try to add the 3 lines into the build.gradle too.