I receive the following error on each file when trying to upload data. Failed to upload Noise (99).wav: nextval: reached maximum value of sequence “project_raw_data_id_seq” (2147483647).
Can anyone help with this?
I receive the following error on each file when trying to upload data. Failed to upload Noise (99).wav: nextval: reached maximum value of sequence “project_raw_data_id_seq” (2147483647).
Can anyone help with this?
Thanks @glowes1985 for reporting this, let me check with the tech team to see if we have any maintenance underway. I have confirmed the same issue is happening for me.
Best
Eoin
Hi @glowes1985
Our tech team found the issue and has restored the upload functionality, thanks again for the report and apologies for any inconvenience!
Best
Eoin
When I generate features, the sample is deleted and cant be accessed.
Hello @glowes1985
could you please share more details? were you able to upload the samples? did you re-generate geatures?
Yes upload was fine. I can go through the entire process of training a model but for some reason the features explorer page and model data explorer page all samples are marked as deleted samples. I used to be able to play each of the samples but doesnt seem to work now.
I face the same problem,too.All procesures are right,and one week ago, I did the same job.It worked well
@wei_solitude Yes, see Issues with feature explorer / data explorer - we’re testing out a fix right now.
Hi @janjongboom, I have been running into issues today with deployment and the run time of the classifier on STM32 hardware. Yesterday I created a CMSIS pack as I have done previously and the execution time was around 150ms which is near to the EI estimate based on my STM32 hardware. Today I have been trying different models and the execution time was up at 2.1s which was very strange. In a last check I went back to my project from yesterday and retrained it without changing any parameters and produced a new CMSIS pack and the execution time is again over 2 seconds. If I install my CMSIS pack from yesterday it is fine at 150ms. Could this be related to todays issue as I cant make sense why an identical setup for a model only retrained would have a radically different execution time to run the classifier. Thanks