These functions were removed in Tensorflow version 2.6. See details for how to update your code:
predict_proba(object, x, batch_size = NULL, verbose = 0, steps = NULL)predict_classes(object, x, batch_size = NULL, verbose = 0, steps = NULL)
Keras model object
Input data (vector, matrix, or array). You can also
pass a tfdataset or a generator returning a list with (inputs, targets) or
(inputs, targets, sample_weights).
Integer. If unspecified, it will default to 32.
Verbosity mode, 0, 1, 2, or "auto". "auto" defaults to 1
for for most cases and defaults to verbose=2 when used with
ParameterServerStrategy or with interactive logging disabled.
Total number of steps (batches of samples) before declaring the
evaluation round finished. The default NULL is equal to the number of
samples in your dataset divided by the batch size.
How to update your code:
predict_proba(): use predict() directly.
predict_classes():
If your model does multi-class classification:
(e.g. if it uses a softmax last-layer activation).
model %>% predict(x) %>% k_argmax()
if your model does binary classification
(e.g. if it uses a sigmoid last-layer activation).
model %>% predict(x) %>% `>`(0.5) %>% k_cast("int32")
The input samples are processed batch by batch.
Other model functions:
compile.keras.engine.training.Model(),
evaluate.keras.engine.training.Model(),
evaluate_generator(),
fit.keras.engine.training.Model(),
fit_generator(),
get_config(),
get_layer(),
keras_model_sequential(),
keras_model(),
multi_gpu_model(),
pop_layer(),
predict.keras.engine.training.Model(),
predict_generator(),
predict_on_batch(),
summary.keras.engine.training.Model(),
train_on_batch()