Timeline for AttributeError: 'Tensor' object has no attribute 'numpy' while extending keras sequential model
Current License: CC BY-SA 4.0
Post Revisions
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 1, 2022 at 17:06 | vote | accept | Salman | ||
| Mar 1, 2022 at 13:39 | comment | added | Salman |
It will be used like: y_pred = KMeans(self.output_shape).fit_predict(inputs.numpy())
|
|
| Mar 1, 2022 at 13:38 | comment | added | Salman | This function is the Kmeans from 'sklearn' package. New layer basically is a clustering layer and I've defined new loss function based on the result of the clusters | |
| Mar 1, 2022 at 13:35 | comment | added | Salman | this package helps me in calculating the loss. so I will call it during the training as well. | |
| Mar 1, 2022 at 13:33 | comment | added | AloneTogether | Do you just want to use the output of your third-party function during inference or also during training? | |
| Mar 1, 2022 at 13:15 | answer | added | MD Mushfirat Mohaimin | timeline score: 2 | |
| S Mar 1, 2022 at 12:57 | history | suggested | Sunderam Dubey | CC BY-SA 4.0 |
Removed thankful messages
|
| Mar 1, 2022 at 12:56 | comment | added | Salman | I need to pass the inputs to a third-party package to do some calculations, which only supports numpy as an input | |
| Mar 1, 2022 at 12:53 | comment | added | AloneTogether |
Why are you calling inputs.numpy()?
|
|
| Mar 1, 2022 at 12:50 | review | Suggested edits | |||
| S Mar 1, 2022 at 12:57 | |||||
| Mar 1, 2022 at 12:49 | history | asked | Salman | CC BY-SA 4.0 |