I want to convert a Tensorflow model with the following structure to a .mlmodel file for use in an iOS app:
cub_image_experiment/
logdir/
val_summaries/
test_summaries/
finetune/
val_summaries/
cmds.txt
config_train.yaml
config_test.yaml
I'm following this tutorial: https://github.com/visipedia/tf_classification/wiki/CUB-200-Image-Classification
However, I'm having trouble understanding the structure of the project. Which files are important and how do I convert all the separate config files and everything into a single .mlmodel file so that I can use in my application?
I've looked online and all I could find was how to convert .caffemodel to .mlmodel or .pb file to .mlmodel. These are all single files, however my project has multiple files. I found a tutorial on how to convert a tf model into a single .pb file, however, that model's structure was different and it did not contain any yaml files. My project is not focused on creating a model at the moment, but merely integrating a model into an iOS app. I found this model interesting for an app idea and wanted to know if it can be integrated. If there are any tutorials out there that might help me in this sort of problem please let me know.
None of that stuff is used by the Core ML model. The yaml files etc are used only to train the TF model.
All you need to provide is a frozen graph (a .pb file) and then convert it to an mlmodel using tfcoreml.
It looks like your project doesn't have a frozen graph but checkpoints. There is a TF utility that you can use to convert the checkpoint to a frozen graph, see https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/freeze_graph.py
Related
I'm kinda new to TensorFlow and Keras, so please excuse any accidental stupidity, but I have an issue. I've been trying to load in models from the TensorFlow Detection Zoo, but haven't had much success.
I can't figure out how to read these saved_model folders (they contain a saved_model.pb file, and an assets and variables folder), so that they're accepted by Keras. Nor can I figure out a way to convert these models so that they may be loaded in. I've tried converting the SavedModel to ONNX, and then convert the ONNX-model to Keras, but that didn't work. Trying to load the original model as a saved_model, and then trying to to save this loaded model in another format gave me no success either.
Since you are new to Tensorflow (and I guess deep learning) I would suggest you stick with the API because the detection zoo models best interface with the object detection API. If you have already downloaded the model, you just need to export it using the exporter_main_v2.py script. This article explains it very well link.
What I'm trying to do
I'm trying to learn TensorFlow object recognition and as usual with new things, I scoured the web for tutorials. I don't want to involve any third party cloud service or web development framework, I want to learn to do it with just native JavaScript, Python, and the TensorFlow library.
What I have so far
So far, I've followed a TensorFlow object detection tutorial (accompanied by a 5+ hour video) to the point where I've trained a model in Tensorflow (python) and want to convert it to run in a browser via TensorflowJS. I've also tried other tutorials and haven't seemed to find one that explains how to do this without a third party cloud / tool and React.
I know in order to use this model with tensorflow.js my goal is to get files like:
group1-shard1of2.bin
group1-shard2of2.bin
labels.json
model.json
I've gotten to the point where I created my TFRecord files and started training:
py Tensorflow\models\research\object_detection\model_main_tf2.py --model_dir=Tensorflow\workspace\models\my_ssd_mobnet --pipeline_config_path=Tensorflow\workspace\models\my_ssd_mobnet\pipeline.config --num_train_steps=100
It seems after training the model, I'm left with:
files named checkpoint, ckpt-1.data-00000-of-00001, ckpt-1.index, pipeline.config
the pre-trained model (which I believe isn't the file that changes during training, right?) ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8
I'm sure it's not hard to get from this step to the files I need, but I honestly browsed a lot of documentation and tutorials and google and didn't see an example of doing it without some third party cloud service. Maybe it's in the documentation, I'm missing something obvious.
The project directory structure looks like this:
Where I've looked for an answer
For some reason, frustratingly, every single tutorial I've found (including the one linked above) for using a pre-trained Tensorflow model for object detection via TensorFlowJS has required the use of IBM Cloud and ReactJS. Maybe they're all copying from some tutorial they found and now all the tutorials include this, I don't know. What I do know is I'm building an Electron.js desktop app and object detection shouldn't require network connectivity assuming the compute is happening on the user's device. To clarify: I'm creating an app where the user trains the model, so it's not just a matter of one time conversion. I want to be able to train with Python Tensorflow and convert the model to run on JavaScript Tensorflow without any cloud API.
So I stopped looking for tutorials and tried looking directly at the documentation at https://github.com/tensorflow/tfjs.
When you get to the section about importing pre-trained models, it says:
Importing pre-trained models
We support porting pre-trained models from:
TensorFlow SavedModel
Keras
So I followed that link to Tensorflow SavedModel, which brings us to a project called tfjs-converter. That repo says:
This repository has been archived in favor of tensorflow/tfjs.
This repo will remain around for some time to keep history but all
future PRs should be sent to tensorflow/tfjs inside the tfjs-core
folder.
All history and contributions have been preserved in the monorepo.
Which sounds a bit like a circular reference to me, considering it's directing me to the page that just told me to go here. So at this point you're wondering well is this whole library deprecated, will it work or what? I look around in this repo anyway, into: https://github.com/tensorflow/tfjs-converter/tree/master/tfjs-converter
It says:
A 2-step process to import your model:
A python pip package to convert a TensorFlow SavedModel or TensorFlow Hub module to a web friendly format. If you already have a converted model, or are using an already hosted model (e.g. MobileNet), skip this step.
JavaScript API, for loading and running inference.
And basically says to create a venv and do:
pip install tensorflowjs
tensorflowjs_converter \
--input_format=tf_saved_model \
--output_format=tfjs_graph_model \
--signature_name=serving_default \
--saved_model_tags=serve \
/mobilenet/saved_model \
/mobilenet/web_model
But wait, are the checkpoint files I have a "TensorFlow SavedModel"? This doesn't seem clear, the documentation doesn't explain. So I google it, find the documentation, and it says:
You can save and load a model in the SavedModel format using the
following APIs:
Low-level tf.saved_model API. This document describes how to use this
API in detail. Save: tf.saved_model.save(model, path_to_dir)
The linked syntax extrapolates somewhat:
tf.saved_model.save(
obj, export_dir, signatures=None, options=None
)
with an example:
class Adder(tf.Module):
#tf.function(input_signature=[tf.TensorSpec(shape=[], dtype=tf.float32)])
def add(self, x):
return x + x
model = Adder()
tf.saved_model.save(model, '/tmp/adder')
But so far, this isn't familiar at all. I don't understand how to take the results of my training process so far (the checkpoints) to load it into a variable model so I can pass it to this function.
This passage seems important:
Variables must be tracked by assigning them to an attribute of a
tracked object or to an attribute of obj directly. TensorFlow objects
(e.g. layers from tf.keras.layers, optimizers from tf.train) track
their variables automatically. This is the same tracking scheme that
tf.train.Checkpoint uses, and an exported Checkpoint object may be
restored as a training checkpoint by pointing
tf.train.Checkpoint.restore to the SavedModel's "variables/"
subdirectory.
And it might be the answer, but I'm not really clear on what it means as far as being "restored", or where I go from there, if that's even the right step to take. All of this is very confusing to someone learning TF which is why I looked for a tutorial that does it, but again, I can't seem to find one without third party cloud services / React.
Please help me connect the dots.
You can convert your model to TensorFlowJS format without any cloud services. I have laid out the steps below.
I'm sure it's not hard to get from this step to the files I need.
The checkpoints you see are in tf.train.Checkpoint format (relevant source code that creates these checkpoints in the object detection model code). This is different from the SavedModel and Keras formats.
We will go through these steps:
Checkpoint (current) --> SavedModel --> TensorFlowJS
Converting from tf.train.Checkpoint to SavedModel
Please see the script models/research/object_detection/export_inference_graph.py to convert the Checkpoint files to SavedModel.
The code below is taken from the docs of that script. Please adjust the paths to your specific project. --input_type should remain as image_tensor.
python export_inference_graph.py \
--input_type image_tensor \
--pipeline_config_path path/to/ssd_inception_v2.config \
--trained_checkpoint_prefix path/to/model.ckpt \
--output_directory path/to/exported_model_directory
In the output directory, you should see a savedmodel directory. We will use this in the next step.
Converting SavedModel to TensorFlowJS
Follow the instructions at https://github.com/tensorflow/tfjs/tree/master/tfjs-converter, specifically paying attention to the "TensorFlow SavedModel example". The example conversion code is copied below. Please modify the input and output paths for your project. The --signature_name and --saved_model_tags might have to be changed, but hopefully not.
tensorflowjs_converter \
--input_format=tf_saved_model \
--output_format=tfjs_graph_model \
--signature_name=serving_default \
--saved_model_tags=serve \
/mobilenet/saved_model \
/mobilenet/web_model
Using the TensorFlowJS model
I know in order to use this model with tensorflow.js my goal is to get files like:
group1-shard1of2.bin
group1-shard2of2.bin
labels.json
model.json
The steps above should create these files for you, though I don't think labels.json will be created. I am not sure what that file should contain. TensorFlowJS will use model.json to construct the inference graph, and it will load the weights from the .bin files.
Because we converted a TensorFlow SavedModel to a TensorFlowJS model, we will need to load the JS model with tf.loadGraphModel(). See the tfjs converter page for more information.
Note that for TensorFlowJS, there is a difference between a TensorFlow SavedModel and a Keras SavedModel. Here, we are dealing with a TensorFlow SavedModel.
The Javascript code to run the model is probably out of scope for this answer, but I would recommend reading this TensorFlowJS tutorial. I have included a representative javascript portion below.
import * as tf from '#tensorflow/tfjs';
import {loadGraphModel} from '#tensorflow/tfjs-converter';
const MODEL_URL = 'model_directory/model.json';
const model = await loadGraphModel(MODEL_URL);
const cat = document.getElementById('cat');
model.execute(tf.browser.fromPixels(cat));
Extra notes
... Which sounds a bit like a circular reference to me,
The TensorFlowJS ecosystem has been consolidated in the tensorflow/tfjs GitHub repository. The tfjs-converter documentation lives there now. You can create a pull request to https://github.com/tensorflow/tfjs to fix the SavedModel link to point to the tensorflow/tfjs repository.
What are the step-by-step instructions for using a TFlite file and embedding it in an actual Android application? For reference, this is regression. Input will be an image, output should be a number. I have already looked at the TensorFlow documentation but they do not explain how to do it from scratch.
The following steps are required to use TFLite in Android:
include the dependency 'org.tensorflow:tensorflow-lite:+' to your build.gradle
Make sure files of type .tflite will not be compressed using the aaptOptions in your build.gradle
Make the model .tflite file available by putting it into your apps assets folder (To create one, right click res folder, click res > New > Folder > Assets Folder)
In your java class that will handle the inference, import the tflite interpreter
Load the model file as a MappedByteBuffer in your java class
Load the MappedByteBuffer into your TFLite interpreter
Convert input image to float ByteBuffer
Define output array matching the size of your output layer
Use the loaded TFLite interpreter to forward pass the input ByteBuffer through your model and write the prediction to your output array.
Let me know if something is unclear!
For Android applications, here is a quick example of using TF Lite for classification. You may be able to follow a similar structure as here: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/examples/android/app/src/main/java/org/tensorflow/demo/TFLiteImageClassifier.java
I would like to convert a TRT optimized frozen model to saved model for tensorflow serving. Are there any suggestions or sources to share?
Or are there any other ways to deploy a TRT optimized model in tensorflow serving?
Thanks.
Assuming you have a TRT optimized model (i.e., the model is represented already in UFF) you can simply follow the steps outlined here: https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#python_topics. Pay special attention to section 3.3 and 3.4, since in these sections you actually build the TRT engine and then save it to a file for later use. From that point forward, you can just re-use the serialized engine (aka. a PLAN file) to do inference.
Basically, the workflow looks something like this:
Build/train model in TensorFlow.
Freeze model (you get a protobuf representation).
Convert model to UFF so TensorRT can understand it.
Use the UFF representation to build a TensorRT engine.
Serialize the engine and save it to a PLAN file.
Once those steps are done (and you should have sufficient example code in the link I provided) you can just load the PLAN file and re-use it over and over again for inference operations.
If you are still stuck, there is an excellent example that is installed by default here: /usr/src/tensorrt/samples/python/end_to_end_tensorflow_mnist. You should be able to use that example to see how to get to the UFF format. Then you can just combine that with the example code found in the link I provided.
I've been using tensorflow image recognition. I've build many scripts which interact with classify_image.py.
I also retrained the model using retrain.py, with my own dataset.
How can use the two files generated: output_graph.pb, output_labels.txt with classify_image.py ?
Ah, the docs say
If you'd like to use the retrained model in a Python program this example from #eldor4do shows what you'll need to do.
Just copied/edited that one file locally, and python .\edited-retraining-example.py. And that was easy.
Note that if you're on Windows, change all examples of /tmp/... to c:/tmp/....