Hello Can we do the following steps for a simple dataset 1. Encode our text into embedding using pre trained models like t5 and then using those text embeddings train a simple lstm to predict the next batch of image embedding tokens (of the codebook in vq vae once the image passes through the encoder) 2. The predicted image embedding tokens will go through the decoder of trained vq-vae to output images. By the way thanks for the video.
Hello, Yes absolutely. In fact in my vqvae video this is exactly what I did. Although I trained a lstm to generate sequence of codebook tokens unconditionally(and then the step 2 that you mentioned), but all one would need to change is just prepend the condition representation to the codebook token sequence to have lstm generate data conditionally. If you are interested you can take a look at that here - th-cam.com/video/1ZHzAOutcnw/w-d-xo.html
Happy diwali to you too :) I am still able to download from the webpage but I have anyway also updated README with the curl command that you can use to download. Can you try with that? github.com/explainingai-code/Dalle-Pytorch/blob/main/README.md#data-preparation
Github Code - github.com/explainingai-code/Dalle-Pytorch
Subscribed. Saw this video on my lab projector. Hope you keep on doing the great work. You deserve more subscribers✌️
Thank you!
Thank you sir.Hope you keep doing the great work.🙏
Thank you Advait :)
Hello Can we do the following steps for a simple dataset
1. Encode our text into embedding using pre trained models like t5 and then using those text embeddings train a simple lstm to predict the next batch of image embedding tokens (of the codebook in vq vae once the image passes through the encoder)
2. The predicted image embedding tokens will go through the decoder of trained vq-vae to output images.
By the way thanks for the video.
Hello, Yes absolutely. In fact in my vqvae video this is exactly what I did. Although I trained a lstm to generate sequence of codebook tokens unconditionally(and then the step 2 that you mentioned), but all one would need to change is just prepend the condition representation to the codebook token sequence to have lstm generate data conditionally.
If you are interested you can take a look at that here - th-cam.com/video/1ZHzAOutcnw/w-d-xo.html
Sir i am not able to dowbload texture images from ALOT homepage .. please help me with its alternative..and happy diwali
Happy diwali to you too :)
I am still able to download from the webpage but I have anyway also updated README with the curl command that you can use to download.
Can you try with that?
github.com/explainingai-code/Dalle-Pytorch/blob/main/README.md#data-preparation
please help sir
@@pratyanshvaibhav Did the curl command not work ?
@@Explaining-AI Thanks a lot sir it worked for me..This channel is really a blessing for me