Impulse Communications, Inc.

When I use one classifier it works fine, but when I use multiple classifiers it always gives an error related to pickling. Here's my code: ml_predictor = Predictor(type_of_estimator='classifier', column_descriptions=column_descriptions) models...

On a new Ubuntu 16.04 AWS GPU server that I set up today using the Deep Learning AMI at https://aws.amazon.com/marketplace/pp/B077GCZ4GR I get an error. I pip3 installed the latest versions...

Retiarii - How To Get Final Model

6

I am following your tutorial at https://nni.readthedocs.io/en/latest/tutorials/hello_nas.html and it runs fine, but I don't understand how to get the final results unless I am watching the experiment while it is...

I understand the 4 parameters in your jQuery form (prefix, length, temperature, top_k) but in the .app file, there are also these 4 lines: top_p=float(params.get('top_p', 0)), truncate=params.get('truncate', None), include_prefix=str(params.get('include_prefix', True)).lower()...

I can load HyperImageAugment like: from kerastuner.applications HyperImageAugment but what is an example of how to actually use it?

CARS Accuracy Metric Question

1

I am using a custom dataset with CARS and it runs fine, but I am confused because it shows a different accuracy at the end of the search part than...

Problem getting accuracy predictions

5

When I add the code to get an accuracy score, I get an error. The code I added was: y_pred = DSL_learner.predict(X_train, y_train) y_pred = numpy.argmax(y_pred,axis=1) I am using numpy...

Requirement.txt File

1

Your instructions refer to a requirement.txt file but there isn't one in your repo.

Scores Too Low

3

I don't get any errors, but when I run play.py for Breakout using your sample weights, it gets scores of only a few points. And if I train the model...

Parallelization

1

Have you looked into parallelizing it? I could not get it to run on my AWS GPU because I had problems with Tensorflow-GPU and CUDA, so I have it running...