Pytorch Image Captioning Tutorial

❤️ Support the channel ❤️

Paid Courses I recommend for learning (affiliate links, no extra cost for you):

✨ Free Resources that are great:

💻 My Deep Learning Setup and Recording Setup:

GitHub Repository:

✅ One-Time Donations:

▶️ You Can Connect with me on:

OUTLINE:
0:00 - Introduction
0:12 - Explanation of Image Captioning
05:15 - Overview of the code
06:07 - Implementation of CNN and RNN
20:03 - Setting up the training
30:36 - Fixing errors
32:18 - Small evaluation and ending

[ashkankhademian]

How is it that you are so good at explaining?
Keep up the good work champ.

[백이음]

u r such a great engineer!
I found out this vid sooo useful!!
Thanks!!!!

[nunenuh]

thank you very much for your videos, please continue your work, many people need your video

[HARIS-qn]

since you feed the feature vector at timestamp-0 so at inference time we also only feed the feature-vector at timestamp-0 we not have to provide the start token in the test phase

[oskarjung]

That was a very Aladdin tutorial, thank you!

[Bobobhehe]

Awesome complete tutorial, thank you.

[vincentchong]

3:37 feed predicted words as input, difference connection for inference and training

[garikhakobyan]

looking forward to new videos. awesome!

[junhuajlake]

OK, I have known it. Excellent Pytorch Tutorial.

[zehrayavuz]

what are the benefits of using lstm instead of transformers in this specific image to text task?

[NutSorting]

Awesome tutorial, followed it till the end. I have a question, where do we split the training and test set? and how as there are image data and caption data too. Can you help me with that?

[rahulseetharaman]

Hi Aladdin, thanks for the awesome tutorials.
Could you please elaborate on 27:51, this statement
outputs=model(imgs, captions[:-1])
Why are we ignoring the last row ? The last row would mostly contain padded characters, and very few EOS indexes. Could you please explain how ignoring the last row works in this context ?
Thanks

[rohinim]

Amazing tutorial!!
Can we do it using the transformer instead of LSTM?

[MatanFainzilber]

Thanks alot! one important question:
In the training loop the loss is calculated from scores and the captions which are the target.
there is no shifting to the right of the target captions. Without doing so how does the model still knows to learn the next word? Is there an internal pytorch method that does so implicitly? I tried to look and i dont understand how in this way the loss can be calculated in a way such the model would learn to predict the next word

[amaulearyan]

Hi I wana know how you had practiced pytorch in your learning journey and so comfortable writing it as till of now i can just write some simple structure but these type, need your help regarding this.

[verakorzhova]

Great tutorial!!! But how to save model?

[soumyajahagirdar]

can we have a demo on visual question generation also?

[aboalifan]

Hi Aladdin, thanks so much for this awesome series of videos. Could you please explain how to use BERT instead of RNN in this model ? thanks in advance

[krishnachauhan]

Please make one vedio for attention in audio processing ex. Speech emotion

[muhammadzubairbaloch]

very good work . please make some videos on medical imaging . thanks