Размер видео: 1280 X 720853 X 480640 X 360
Показать панель управления
Автовоспроизведение
Автоповтор
One of the best explanations I have been able to find. Thank you for your time and effort!
This seems to be an incredible tool for ML practitioners. I can't wait to start using it!!!
Amazing video , very clearly explained optuna !
Glad it was helpful!
Yeah! We are no longer need to do fine-tuning.I used an Adma with 1e-3 with the same setting but I was beaten by an SGD 1e-4 with the same setting.That notebook was the Pytorch official fast R-CNN fine-tuning notebook.
This tool seems to be incredible, i will be sure to include it in my next project, thanks :)
This is great, a lot easier to use than hyperopt.
Where to find gaussian sampler?
Great explanation
thank you, very nice presentation
want to know how to implement the progress bar at 12:45, it looks pretty cool
use library called tqdm and then set progress bar mode to ascii
Great tool ! Thank you for sharing
Appreciated
Where can i find quality code examples?
Excellent video!
Thank you for the video!
a great useful framework thank u
Awesome video and for thx to show this tool!
The provided link to the source code is not available.
Brilliant.
Amazing!
would be awesome to have this integrated with MLFlow!
could you share the slides?
Windows pip build seems to be broken, I had to install with conda
that is very common unfortunately, do you have C++ compilers installed on Win?
14:37 Never though learning rate is so important
11:10 twice as fast WITH tuning.
One of the best explanations I have been able to find. Thank you for your time and effort!
This seems to be an incredible tool for ML practitioners. I can't wait to start using it!!!
Amazing video , very clearly explained optuna !
Glad it was helpful!
Yeah! We are no longer need to do fine-tuning.
I used an Adma with 1e-3 with the same setting but I was beaten by an SGD 1e-4 with the same setting.
That notebook was the Pytorch official fast R-CNN fine-tuning notebook.
This tool seems to be incredible, i will be sure to include it in my next project, thanks :)
This is great, a lot easier to use than hyperopt.
Where to find gaussian sampler?
Great explanation
thank you, very nice presentation
want to know how to implement the progress bar at 12:45, it looks pretty cool
use library called tqdm and then set progress bar mode to ascii
Great tool ! Thank you for sharing
Appreciated
Where can i find quality code examples?
Excellent video!
Thank you for the video!
a great useful framework thank u
Awesome video and for thx to show this tool!
The provided link to the source code is not available.
Brilliant.
Amazing!
would be awesome to have this integrated with MLFlow!
could you share the slides?
Windows pip build seems to be broken, I had to install with conda
that is very common unfortunately, do you have C++ compilers installed on Win?
14:37 Never though learning rate is so important
11:10 twice as fast WITH tuning.