We Keep Coding

Save and reuse ML model

First of all, let me introduce myself. I am a young researcher and I am interested in machine learning. I created a model, trained, tested and validated. Now I would like to know if there is a way to save my trained model.
I am also interested in knowing if the model is saved trained.
Finally, is there a way to use the saved (and trained) model with new data without having to train the model again?
I work with python!

Welcome to the community.
Yes, you may save the trained model and reuse it later. There are several ways to do so and I will introduce you to a couple of them here. However, please note which library you used to build your model and use a method for that library.
Pickel: Pickle is the standard way of serializing objects in Python.
import pickle
pickle.dump(model, open(filename, 'wb'))
loaded_model = pickle.load(open(filename, 'rb'))
Joblib: Joblib is part of the SciPy ecosystem and provides utilities for pipelining Python jobs.
import joblib
joblib.dump(model, filename)
loaded_model = joblib.load(filename)
Finally, as suggested by others, if you used libraries such as Tensorflow to build and train your models, please note that they have extensive ways to work with the built model and save/load it. Please check the following information:
Tensorflow Save and Load model

There may be a better way to do this but this is how I have done it before, with python.
So you have a ML model that you have trained. That model is basically just a set of parameters. Depending on what module you are using, you can save those parameters in a file, and import them to regenerate your model later.
Perhaps a simpler way is to save the model object entirely in a file using pickling.
https://docs.python.org/3/library/pickle.html
You can dump the object into a file, and load it back when you want to run it again.

Hugging Face model Bio_ClinicalBERT producing 404 error

I'm building a Named Entity Recognition (NER) model using the Hugging Face implementation of emilyalsentzer/Bio_ClinicalBERT. Up to today, I've had no issues with the model. I'm hopeful that someone can help me understand why it's currently not working as expected.
Question 1 - today, trying to train using:
MODEL_NAME = 'emilyalsentzer/Bio_ClinicalBERT'
model = text.sequence_tagger('bilstm-bert', preproc, bert_model=MODEL_NAME)
results in this error:
404 Client Error: Not Found for url: https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT/resolve/main/tf_model.h5
Does Hugging Face offer any kind of health check to ascertain the status of their models?
Question 2 - working with files (model.h5, model.json, and preproc.sav) I'd saved from earlier training iterations, I'm getting the same 404 error shown above. I don't understand wherein these files the call to Hugging Face is occurring. It doesn't seem to be in the .json, and the .h5 and .sav file formats are hard to inspect. Read more about what these files are:
https://medium.com/analytics-vidhya/how-to-deploy-your-neural-network-model-using-ktrain-ae255b134c77
Back in February, I'd used these exact model.h5, model.json, and preproc.sav files to run the NER app using Streamlit, no problem. Not sure if this is temporary issue with Bio_ClinicalBERT or if I need to retool my original approach due to potentially permanent problems with this transformer model.

Judging from the URL you provided for Question 1, I understand that you are trying to load pre-trained weights for a TensorFlow model (tf_model.h5)
However, the pre-trained model you are trying to load is only available in a PyTorch version. Go on the link and look at the tags at the top of the page. This model only has a PyTorch tag, not a Tensorflow tag.
It's my understanding that in this case you should load pre-trained weights from the PyTorch checkpoint. To that end, you would add this parameter to the function that does the loading:
from_pt=True

As mentioned in this post in the ktrain repo, you should be able to safely ignore the error.
The 404 error simply means that transformers was not able to find a Tensorflow version of this particular model (which is being requested by ktrain). If you go to the Hugging Face model hub, you'll see that the model you're using was only uploaded as a PyTorch model.
In cases like this, the PyTorch version of the model checkpoint will be automatically downloaded by ktrain and then loaded as a Tensorflow model for training/fine-tuning. If you type model.summary(), it should show that the model was loaded successfully.
The reason you didn't see the error before is because newer versions of Hugging Face transformers show the 404 error, I think.

How to use custom Tensorflow Lite model

I am very new to machine learning. I have a python file with a very simple TensorFlow model that I need to deploy on Android using Google's ML Kit (which would be creating tflite file). I absolutely don't understand what should be the structure of my python file and Google's documentation doesn't make it any easier. Maybe someone has a good example of converting CUSTOM MODEL WRITTEN FROM SCRATCH and then using it in Java. I need to pass a string from Android's text field and get a predicted answer.

You need to first train your model on whatever the dataset you have. The layers in the model must comply with the supported layers by the TFLite library. Here is a list of layers that are supported and unsupported.
Once you have trained it, based on how you saved it (Let's say using kerasmodel.save). Convert it to TFLite following this tutorial or other tutorials on this page.
Now you can use this .tflite model in Android studio. For this you can follow this good tutorial.

Loading pre-trained resnet model to cleverhans model format

I am trying to load a pre-trained ResNet model from the MadryLab CIFAR-10 challenge into CleverHans to compute transfer attacks.
However restoring the saved models into the model_zoo.madry_lab_challenges.cifar10_model.ResNet object does not work. It appears to restore fine initially, but when I try to actually use the model, I get an error such as:
Attempting to use uninitialized value
ResNet/unit_3_1/residual_only_activation/BatchNorm/moving_mean
The easiest way to reproduce this error is to actually just run the provided attack_model.py example included in CleverHans here:
https://github.com/tensorflow/cleverhans/blob/master/examples/madry_lab_challenges/cifar10/attack_model.py
It encounters the same error after loading the model when it tries to use it, on both adv_trained and naturally_trained models.
Is there a workaround to this problem?
It seems the other option is to use the cleverhans.model.CallableModelWrapper instead, but I haven't been able to find an example of how to use that.

Deploying TensorFlow Checkpoint to Google Cloud Platform

I have trained a TensorFlow model and saved a checkpoint, and would like to deploy it to Google Cloud Platform. In the model deployment documentation it says that you need to create a SavedModel. It seems that others also use checkpoints instead of SavedModel.
Given that I have already spent time training this model and only have checkpoints instead of a SavedModel, is there a method I can use to deploy the model still or will I need to retrain?

A checkpoint maps variable names to tensor values. This, as is, is not enough for higher-level systems to use your model. On the other hand, a SavedModel is complete and airtight. As is made clear in the answer you link to in your post, a SavedModel provides all the info needed for serving TensorFlow models: a set of MetaGraphs, a checkpoint compatible with these Graphs and all necessary asset files. If you look at it this way, it makes sense that you need to export your model to a SavedModel in order to deploy it to ML Engine. Now, this does not imply that you need to retrain. What you need to do instead is to wrap one of your checkpoints into a SavedModel.