Keras model taking too long to train
So I have the following model for sentiment analysis (using pre trained word embeddings):
And as visible, I have a pre trained embedding matrix and only about 500k trainable parameters. So why does it take a whole eternity to train this model? The batch size is 128 and number of epochs is 25. And the ETA for first epoch is about 10 minutes. I haven't even completed that.
Just to mention, I am not using CUDA or anything. I don't think I have a GPU enabled Tensorflow. And I'm willing to do anything to increase the speed. And I have Tensorflow 2.1.0.
And here's the answer I am not using CUDA or anything. Training on CPU is much slower than on GPU. If you don't have high-performance enough video card, you can use several services such as Google Colab or Kaggle
- How do I import TensorFlow in Python?
- Selecting default search engine is needed for Chrome version 127
- Obtain eigen values and vectors from sklearn PCA
- what is the meaning of index[",i,"] in a loop?
- Why do I get NotImplementedError trying to create a dataframe from a database table?
- Getting list of all satellites crossing over my location in the next 24 hours
- pd.to_datetime() not consistently working to convert objects
- web scraping of webpage on chartink.com
- How do I get VideoCapture to return errors instead of warnings?
- How to pass input dim from fit method to skorch wrapper?
- Why the warning: "FutureWarning: Setting an item of incompatible dtype is deprecated and will raise an error in a future version of pandas"?
- ImportError: No module named common
- Python win32serviceutil QueryServiceStatus: What does the return value mean?
- How to stop numpy floats being displayed as "np.float64"?
- VS Code does not change python environment
- Find the index of the k smallest values of a numpy array
- N choose r possibilities as increasing binary numbers
- Polars / Python Limits Number of Printed Table Output Rows
- Ebay Python SDK returning an error only on specific item categories
- Why does %timeit loop different number of times?
- What is the most efficient way to multiprocess over a very large dataframe?
- Is there a way to catch unittest exceptions with PyCharm?
- what are all the key names in keyboard module?
- Make virtualenv with specific Python version (MacOS)
- Python & OpenCV: How to crop half-formed bounding boxes
- What is the proper way to type hint the return value of an @asynccontextmanager?
- How to merge an upper and lower triangular, also adding a diagonal of 1s
- Class cannot subclass 'QObject' (has type 'Any') using mypy
- Type hints: when to annotate
- How should a NamedTemporaryFile be annotated?