Video

I have come to understand attention as key, query, value multiplication/addition. Do you know why this wasn't used and if it's appropriate to call it attention?

Excellent overview. Appreciate it!

There was a error on your published code but not in the video. attn_output, attn_output_weights = self.att(x, x, x) It should be attn_output, attn_output_weights = self.att(q, k, v) Anyway, thanks for sharing the video and code base. It helped me a lot while learning ViT

Great video. Amazing stuff. I have a query. In this use case, it is assumed the distance-based calculations formulate the edge index, and hence, it is constant. How we should proceed if the edges/edge indexes change for every time snapshot.

You are amazing at explaining. Congratulations at having done this so incredibly well

Hi, great video, thanks! Is there a way to use SHAP for ARIMA/SARIMA?

your content and explanation is Incredibly helpful. Thank you

Is this better for the MNIST challenge compared to a simple conv network like LeNet

Awesome!

great video to explain lora！ thanks

Is it okay to not scale the numerical data? Can we just proceed with the analysis as is?

can you please make a video on how to perform inference on VIT like googles open source vision transformer?

Great video! For me, the code makes it easier to understand the math than the actual formulas, so videos like these really help.

great video....

this is really amazing content but there is a problem on colab this code is not work anymore

great video , thanks for the work! here is a question from a complete beginner of mlflow and deployment: do I need 3 different machines to run the servers seperately ? Thanks!

Great talk. It’s very clearly explained and well presented.

good job!

For the line "from torch_geometric_temporal.dataset import METRLADatasetLoader" I am getting this error, "ModuleNotFoundError Traceback (most recent call last) <ipython-input-5-ab694df90048> in <cell line: 2>() 1 import numpy as np ----> 2 from torch_geometric_temporal.dataset import METRLADatasetLoader 3 from torch_geometric_temporal.signal import StaticGraphTemporalSignal 4 5 loader = METRLADatasetLoader() 3 frames /usr/local/lib/python3.10/dist-packages/torch_geometric_temporal/nn/attention/tsagcn.py in <module> 4 import torch.nn as nn 5 from torch.autograd import Variable ----> 6 from torch_geometric.utils.to_dense_adj import to_dense_adj 7 import torch.nn.functional as F 8 ModuleNotFoundError: No module named 'torch_geometric.utils.to_dense_adj'" Can you kindly guide that what could be the issue?

Excellent.

Explained quite well !

I've changed the output layer a bit... this: self.head_ln = nn.LayerNorm(emb_dim) self.head = nn.Sequential(nn.Linear(int((1 + self.height/self.patch_size * self.width/self.patch_size) * emb_dim), out_dim)) Then in forward: x = x.view(x.shape[0], int((1 + self.height/self.patch_size * self.width/self.patch_size) * x.shape[-1])) out = self.head(x) The downside is that you'll likely get a lot more overfitting, but without it the network was not really training at all.

BEST DIMENSIONAL REDUCTION VIDEO SERIES EVER! You are the 3blue1brown for data mining.

I think there is a confusion between cls token and positional embedding? At 6:09?

Finally a channel with good content!

hi there I have used the code for binary class classification, but encountering the problem on accuracy , showing 100% accuracy only on label 1 and some times on label 2. So it would be helpful for me if u provide me any solution

Very useful and informative video, especially PointNet and batch size parts. Special thanks for using point cloud domain!

Where to get slides? Used in video

how is Lora fine-tuning track changes from creating two decomposition matrix? How the ΔW is determined?

This channel is a gift

Ideot read paper. Lol

Your videos are great, super high quality and clear explanations. Thanks you so much!

Thank you sir! Your videos are great! 👍

Perfect! Just in time for my ML final lmao

Brilliant

The video is great but the training in the code didn't work for the entire 1000 epochs. Despite the code looks logical, there is endless of things that can go wrong so I think it was better to do a tutorial with working ViT notebook.

This work is crazy good!!

hello, nice work!! Can you do more video about combinning graph neural netwwork and recurrent network, i cannot find that anywhere

great video, thanks

What an excellent video!! Congrats!!

beutifully explained

Thank you very much for this amazing vide. However, although this was probably only for demo purposes of a forward pass after LoRA finetuning; the modified forward pass method you`ve shown might be mislieading; since the forward pass of the function is assumed to be entirely linear. So, does the addition of the LoRA finetuned weights to the base model weights happen directly within model weights file (like .safetensors) or can it be done on a higher level on pytorch or tensorflow?

Thanks a lot Amazing explanation, very clear and straightforward

Also StandfordCars is no longer available can you plese chnage it?

I didnt understand...why do we have to convert images to tensors?

Conversion of Videos From SD to HD Resolution Using Diffusion Source code please

Do you have ppt on this

TLDR: "couldn't make it work but maybe you can"

installation is very difficult