Timeline for How to set batch_size, steps_per epoch, and validation steps?
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 13, 2019 at 6:24 | vote | accept | Ermene | ||
| Sep 28, 2018 at 21:04 | comment | added | Silpion | According to the documentation, the parameter steps_per_epoch of the method fit has a default and thus should be optional: "the default None is equal to the number of samples in your dataset divided by the batch size, or 1 if that cannot be determined." Source: keras.io/models/model | |
| Sep 27, 2018 at 7:09 | comment | added | Nicolas Raoul |
What do you mean by "skipping this parameter"? When I remove the parameter I get When using data tensors as input to a model, you should specify the steps_per_epoch argument.
|
|
| Mar 30, 2018 at 11:16 | history | edited | Silpion | CC BY-SA 3.0 |
added 33 characters in body
|
| Mar 30, 2018 at 11:07 | history | answered | Silpion | CC BY-SA 3.0 |