为什么validation_freq不能与Keras模型配合使用？

Question

According to the Keras docs , fit takes a validation_freq param:

validation_freq: Only relevant if validation data is provided. Integer or list/tuple/set. If an integer, specifies how many training epochs to run before a new validation run is performed, eg validation_freq=2 runs validation every 2 epochs. If a list, tuple, or set, specifies the epochs on which to run validation, eg validation_freq=[1, 2, 10] runs validation at the end of the 1st, 2nd, and 10th epochs.

result = model.fit( X_train, Y_train, epochs=2000, verbose=1, validation_data=(X_test,Y_test), validation_freq=10) # , validation_split=0.2

This raises:

File "/Users/george/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 942, in fit
raise TypeError('Unrecognized keyword arguments: ' + str(kwargs))
TypeError: Unrecognized keyword arguments: {'validation_freq': 10}

Using Keras2.1.6-tf. Has this param been added since?

If so, how to update Keras for Anaconda? I tried:

> conda update keras
Collecting package metadata: done
Solving environment: done

# All requested packages already installed.

Answer 1

The commit that added validation_freq was added after the latest release 2.2.4. See https://github.com/keras-team/keras/commit/a6c8042121371b5873773ca767f28cdf5689d5e4 , which was committed 28 days ago, after the latest release which was released last October.

I fixed this by installing from keras' git repo:

pip uninstall keras
pip install git+git://github.com/keras-team/keras.git

Although you're using conda , pip should still work to install packages. You may have to fiddle around with pip installing to the right python, ie pip3 install or on windows python -m pip install . Worst comes to worst use conda to install from the source on github.