Muye Chen
Muye Chen
> > > > please use 'val_accuracy' replace this 'val_acc' such as this code: history['val_acc'] ---> history['val_accuracy'] @xxs980 I moved the issue to this page. It has worked for the...
At the moment val_loss works but strangely val_accuracy returns the error shown above. ``` val_loss = np.amin(results.history['val_loss']) return {'loss': val_loss, 'status': STATUS_OK, 'model': model} ```
I have deleted all the blocks in markdown and raw text. Exited the notebook, terminated the running command prompt and restarted the kernel. Then hyperas works without issue. Why is...
> it maybe the hyperopt version problem，please choose other version of hyperopt pip install hyperopt==0.2.5 Thank you! It's starting to train now. However there is an additional KeyError issue with...
The further issue with 'val_accuracy' is moved [here](https://github.com/maxpumperla/hyperas/issues/285).
click on the gz data files, you can find the 'download' tab on the rhs
> Which versions of onnxruntime and onnx are you using? I assume it is coming from pypi. You shared an example which is wroking, do you know the differences with...