What is the difference between the predict and predict_on_batch methods of a Keras model?

Question

According to the keras documentation:

predict_on_batch(self, x) Returns predictions for a single batch of samples. 

However, there does not seem to be any difference with the standard predict method when called on a batch, whether it being with one or multiple elements.

model.predict_on_batch(np.zeros((n, d_in))) 

is the same as

model.predict(np.zeros((n, d_in))) 

(a numpy.ndarray of shape (n, d_out)

Answer 1

It seems predict_on_batch is a lot faster compared to predict if executed on a single batch.

• batch & model information
  • batch shape: (1024, 333)
  • batch dtype: float32
  • model parameters: ~150k
• timeit result:
  • predict: ~1.45 seconds
  • predict_on_batch: ~95.5 ms

In summary, predict method has extra operations to ensure a collection of batches are processed right, whereas, predict_on_batch is a lightweight alternative to predict that should be used on a single batch.

Answer 2

The difference lies in when you pass as x data that is larger than one batch.

predict will go through all the data, batch by batch, predicting labels. It thus internally does the splitting in batches and feeding one batch at a time.

predict_on_batch, on the other hand, assumes that the data you pass in is exactly one batch and thus feeds it to the network. It won't try to split it (which, depending on your setup, might prove problematic for your GPU memory if the array is very big)