Understand Inference process in TensorFlow-Lite - tensorflow

I am new to tensorflow lite development and would like to know a guide to understand the code of inference process of any neural network in tflite.
How can I proceed?
Thanks in advance
I have tried to follow the inference flow for a dense neural network.

You can start from here to know what APIs does what and follow from there.
Some high level points
To load TF Lite file you use TfLite Interpreter.
A TFLite graph consists of a list of subgraphs (basically each subgraph can be viewed as a function).
Each subgraph should have operations in execution order and calling Invoke will trigger them in the provided order.

Related

Data augmentation on GPU

As tf.data augmentations are executed only on CPUs. I need a way to run certain augmentations on the TPU for an audio project.
For example,
CPU: tf.recs read -> audio crop -> noise addition.
TPU: spectogram -> Mixup Augmentation.
Most augmentations can be done as a Keras Layer on top of the model, but MixUp requires both changes in input as well as label.
Is there a way to do it using tf keras APIs.
And if there is any way we can transfer part of tf.data to run on TPU that will also be helpful.
As you have rightly mentioned and as per the Tensorflow documentation also the preprocessing of tf.data is done on CPU only.
However, you can do some workaround to preprocess your tf.data using TPU/GPU by directly using transformation function in your model with something like below code.
input = tf.keras.layers.Input((512,512,3))
x = tf.keras.layers.Lambda(transform)(input)
You can follow this Kaggle post for detailed discussion on this topic.
See the Tensorflow guide that discusses preprocessing data before the model or inside the model. By including preprocessing inside the model, the GPU is leveraged instead of the CPU, it makes the model portable, and it helps reduce the training/serving skew. The guide also has multiple recipes to get you started too. It doesn't explicitly state this works for a TPU but it can be tried.

Dumping Weights in TensorflowLite

new Tensorflow 2.0 user. My project requires me to investigate the weights for the neural network i created in Tensorflow (super simple one). I think I know how to do it in the regular Tensorflow case. Namely I use the command model.save_weights(filename). I would like to repeat this effort for a .tflite model but I am having trouble. Instead of generating my own tensorflow lite model, I am using one of the many models which are provided online: https://www.tensorflow.org/lite/guide/hosted_model to avoid having to troubleshoot my use of the Tensorflow Lite converter. Any thoughts?

How to convert model trained on custom data-set for the Edge TPU board?

I have trained my custom data-set using the Tensor Flow Object Detection API. I run my "prediction" script and it works fine on the GPU. Now , I want to convert the model to lite and run it on the Google Coral Edge TPU Board to detect my custom objects. I have gone through the documentation that Google Coral Board Website provides but I found it very confusing.
How to convert and run it on the Google Coral Edge TPU Board?
Thanks
Without reading the documentation, it will be very hard to continue. I'm not sure what your "prediction script" means, but I'm assuming that the script loaded a .pb tensorflow model, loaded some image data, and run inference on it to produce prediction results. That means you have a .pb tensorflow model at the "Frozen graph" stage of the following pipeline:
Image taken from coral.ai.
The next step would be to convert your .pb model to a "fully quantized .tflite model" using the post training quantization technique. The documentation to do that are given here. I also created a github gist, containing an example of Post Training Quantization here. Once you have produced the .tflite model, you'll need to compile the model via the edgetpu_compiler. Although everything you need to know about the edgetpu compiler is in that link, for your purpose, compiling a model is as simple as:
$ edgetpu_compiler your_model_name.tflite
Which will creates a your_model_name_edgetpu.tflite model that is compatible with the EdgeTPU. Now, if at this stage, instead of creating an edgetpu compatible model, you are getting some type of errors, then that means your model did not meets the requirements that are posted in the models-requirements section.
Once you have produced a compiled model, you can then deploy it on an edgetpu device. Currently are 2 main APIs that can be use to run inference with the model:
EdgeTPU API
python api
C++ api
tflite API
C++ api
python api
Ultimately, there are many demo examples to run inference on the model here.
The previous answer works with general classification models, but not with TF object detection API trained models.
You cannot do post-training quantization with TF Lite converter on TF object detection API models.
In order to run object detection models on EdgeTPU-s:
You must train the models in quantized aware training mode with this addition in model config:
graph_rewriter {
quantization {
delay: 48000
weight_bits: 8
activation_bits: 8
}
}
This might not work with all the models provided in the model-zoo, try a quantized model first.
After training, export the frozen graph with: object_detection/export_tflite_ssd_graph.py
Run tensorflow/lite/toco tool on the frozen graph to make it TFLite compatible
And finally run edgetpu_complier on the .tflite file
You can find more in-depth guide here:
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_on_mobile_tensorflowlite.md

Quantization aware training examples?

I want to do quantization-aware training with a basic convolutional neural network that I define directly in tensorflow (I don't want to use other API's such as Keras). The only ressource that I am aware of is the readme here:
https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/quantize
However its not clear exactly where the different quantization commands should go in the overall process of training and then freezing the graph for actual inference.
Therefore I am wondering if there is any code example out there that shows how to define, train, and freeze a simple convolutional neural network with quantization aware training in tensorflow?
It seems that others have had the same question as well, see for instance here.
Thanks!

Evaluate a model created using Tensorflow Object Detection API

I trained a model using Tensorflow object detection API for detecting swimming pools using satellite images. I used 'faster_rcnn_inception_v2_coco_2018_01_28' model for training. I generated a frozen inference graph (.pb). I want to evaluate the precision and recall of the model. Can someone tell me how I can do that, preferably without using pycocotools as I was facing some issues with that. Any suggestions are welcome :)
From the Object Detection API you can run "eval.py" from "models/research/object_detection/legacy/".
Your have to define an evaluation metric in your config file (see the supported evaluation protocols)
For example:
eval_config: {metrics_set: "coco_detection_metrics"}
The Pascal VOC e.g. then gives you the mean Average Precsion (mAP)