Keras Model.fit Verbose Formatting

Question

I\'m running Keras model.fit() in Jupyter notebook, and the output is very messy if verbose is set to 1:

    Train on 6400 samples, validate on 800 samples
    E         


        

Answer 1

You can try the Keras-adapted version of the TQDM progress bar library.

• The original TQDM library: https://github.com/tqdm/tqdm
• The Keras version of TQDM: https://github.com/bstriner/keras-tqdm

The usage instructions can be brought down to:

1. install e.g. per pip install keras-tqdm (stable) or pip install git+https://github.com/bstriner/keras-tqdm.git (for latest dev-version)

2. import the callback function with from keras_tqdm import TQDMNotebookCallback

3. run Keras' fit or fit_generator with verbose=0 or verbose=2 settings, but with a callback to the imported TQDMNotebookCallback, e.g. model.fit(X_train, Y_train, verbose=0, callbacks=[TQDMNotebookCallback()])

The result:

Answer 2

Took me a while to see this but tqdm (version >= 4.41.0) has also just added built-in support for keras so you could do:

from tqdm.keras import TqdmCallback
...
model.fit(..., verbose=0, callbacks=[TqdmCallback(verbose=2)])

This turns off keras' progress (verbose=0), and uses tqdm instead. For the callback, verbose=2 means separate progressbars for epochs and batches. 1 means clear batch bars when done. 0 means only show epochs (never show batch bars).

If there are any issues with it please feel free to post on https://github.com/tqdm/tqdm/issues