Keras Model Training API#

submited by
Style Pass
2024-04-02 01:30:02

A Should return a tuple of either (inputs, targets) or (inputs, targets, sample_weights).

A keras.utils.PyDataset returning (inputs, targets) or (inputs, targets, sample_weights).

Target data. Like the input data x, it could be either NumPy array(s) or backend-native tensor(s). If x is a dataset, generator, or keras.utils.PyDataset instance, y should not be specified (since targets will be obtained from x).

Integer or None. Number of samples per gradient update. If unspecified, batch_size will default to 32. Do not specify the batch_size if your data is in the form of datasets, generators, or keras.utils.PyDataset instances (since they generate batches).

Leave a Comment