Timeline for Keras to_categorical results in different memory allocation error every re-run
Current License: CC BY-SA 4.0
Post Revisions
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 6 at 1:17 | comment | added | Emerald Cross | @xdurch0 I was wondering if this was maybe a common problem with using to_categorical. The classification I'm doing makes use of 512x512 RGB training images with the aim of classifying 11 categories, and so I'm hot encoding the label data. Incidentally, I actually got this to finish running one time without changing anything, so I thought it was okay, but then it started giving me errors again. What other details could I provide? Your reply is much appreciated. | |
| Jan 5 at 8:47 | comment | added | xdurch0 | The reason is that you are allocating too much memory, and the fix would be to use less memory. Given the amount of detail you have provided, that's about all we can say. But if your program ever tries to allocate an array with 276824064 rows, there is most certainly something very wrong with your code. | |
| Jan 5 at 6:50 | history | edited | Emerald Cross | CC BY-SA 4.0 |
added 30 characters in body
|
| Jan 5 at 6:48 | history | edited | Emerald Cross | CC BY-SA 4.0 |
added 10 characters in body
|
| S Jan 5 at 6:40 | review | First questions | |||
| Jan 5 at 9:13 | |||||
| S Jan 5 at 6:40 | history | asked | Emerald Cross | CC BY-SA 4.0 |