Timeline for answer to Why does Keras LSTM batch size used for prediction have to be the same as fitting batch size? by Oren Matar
Current License: CC BY-SA 3.0
Post Revisions
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 9, 2017 at 2:25 | comment | added | Jeremy | Didn't work for me. ValueError: Tensor("Placeholder:0", shape=(4, 24), dtype=float32) must be from the same graph as Tensor("l1_1/kernel:0", shape=(4, 24), dtype=float32_ref). | |
| May 28, 2017 at 20:57 | comment | added | DanielSon | Oren I'm going to try that out, looks like a great solution! | |
| May 28, 2017 at 14:40 | review | First posts | |||
| May 28, 2017 at 14:41 | |||||
| May 28, 2017 at 14:40 | history | answered | Oren Matar | CC BY-SA 3.0 |