the only comprehensive video on tensorboard. I am creating ANN using tensorflow and pytorch from 1 year but never knew the utility of this tool. thanks for sharing this knowledge.
I was really fortunate to stumble upon this tutorial, it's pure gold! Decided to check your other videos on the channel real quick, I've eventually spent the last hour going through them! You're doing an amazing job with your videos, thank you :)
Thank you for this great tutorial. It gives me the main topics I need to check in the docs and the first intuitions about the framework. Keep up with the good stuff!
Extremely well done video, thank you! I'd be curious to hear your thoughts on the various libraries built on top of PyTorch like Pytorch-lightning and fastai/fastai2.
Thank you for the kind words, really appreciate it. I'm very interested in learning more about Pytorch lightning but at this point I'm not too familiar with any of those libraries unfortunately. My view currently is that Fastai seems to be a library built to simplify things further, so that you can build state of the art models without diving into too much details (tailoring to the fastai mindset of a top-down approach).
Hey! I learned a lot from your videos! Just wanna request a video on how to do Confusion Matrix using Pytorch using the code you've been using. As a beginner, I'm having a hard time understanding how to get the metrics required for confusion matrix. Anyway, Thanks!
Thank you for sharing valuable series on Pytorch. At time 19.44 in this video, you are showing orange bar to change the images in different batches, however with same code typed by me, i am not able to get the orange bar. please look into this and suggest.
Everything works for me except the last step of 'embedding projector'. It says: 'warning: Embedding dir exists, did you set global_step for add_embedding()?'
At 6:37 you mention it's not the best way to do hyperparameter search, aren't the learning rates already on a log-10 scale? In any case, do you have other videos exploring hyperparameter search?
10:00 For some reason some of the graphs are totally fine and some doesn't show up at all or they show up but to a very limited step. Did this happen to some of you?
the only comprehensive video on tensorboard. I am creating ANN using tensorflow and pytorch from 1 year but never knew the utility of this tool. thanks for sharing this knowledge.
I appreciate the kind words 🙏
I was really fortunate to stumble upon this tutorial, it's pure gold!
Decided to check your other videos on the channel real quick, I've eventually spent the last hour going through them!
You're doing an amazing job with your videos, thank you :)
I would recommend your videos to my friends who are still struggling with deep learning. Thank you again.
Thank you so much Aladdin, your explanation is great. I'm watching you videos for last two days non-stop. Well done
Your videos are just gold! Thanks for doing this!
Thank you for this great tutorial. It gives me the main topics I need to check in the docs and the first intuitions about the framework. Keep up with the good stuff!
🙏
Your explanations were great. Thank you so much.
Fantastic !! very well done man
Thank you! Very helpful video
Dude, I'm really learning a lot from your videos, thanks and keep up the cool work!
Your videos have helped me a lot!
very nice tuto ! I love your videos !
This is a really cool video, thanks making it !
Glad it was useful :)
Thanks! Very helpful
Great video with clear explanations! I do get insights from your work! Thank you.
Really nice video, I'm inspired to use tensorboard now!
Thanks I appreciate that a lot
This is really helpful, Thanks :)
LOVED IT !
Wow this is awesome!
Extremely well done video, thank you! I'd be curious to hear your thoughts on the various libraries built on top of PyTorch like Pytorch-lightning and fastai/fastai2.
Thank you for the kind words, really appreciate it. I'm very interested in learning more about Pytorch lightning but at this point I'm not too familiar with any of those libraries unfortunately. My view currently is that Fastai seems to be a library built to simplify things further, so that you can build state of the art models without diving into too much details (tailoring to the fastai mindset of a top-down approach).
amazing class
Learnt a lot. Thanks
This is very impressive work! Thank you very much @Aladdin
thanks for the video!
Very good video! Thank you so much. You mentioned in the video that the common way to do hyper parameter search is in log space? What is it?
visdom hope to see that!THANK YOU!
Hey! I learned a lot from your videos! Just wanna request a video on how to do Confusion Matrix using Pytorch using the code you've been using. As a beginner, I'm having a hard time understanding how to get the metrics required for confusion matrix. Anyway, Thanks!
Thank you very much!
Thank you for sharing valuable series on Pytorch. At time 19.44 in this video, you are showing orange bar to change the images in different batches, however with same code typed by me, i am not able to get the orange bar. please look into this and suggest.
thanks for the time.
Does this support writing to remote path directly?
I suggest you move the part of code you are working on in the middle of the screen. It was blocked by the video progress bar all the time.
Everything works for me except the last step of 'embedding projector'. It says: 'warning: Embedding dir exists, did you set global_step for add_embedding()?'
Great video
Thanks I appreciate it :)
At 6:37 you mention it's not the best way to do hyperparameter search, aren't the learning rates already on a log-10 scale? In any case, do you have other videos exploring hyperparameter search?
Thanks bro
THANKS
Hey ,
I tried executing the tensorboard command, but nothing shows up.
10:00
For some reason some of the graphs are totally fine and some doesn't show up at all or they show up but to a very limited step.
Did this happen to some of you?
For some reason some of the graphs are totally fine and some show up very limited step.
Csn we visualize rgb images in tsne?
Yeah if I remember correctly I tried it on CIFAR10 as well, but perhaps I didn't show that in the video