Thanks for the video Sam, this was helpful! I might recommend making these files more easy to find? It would be really useful to me if I could just get the file in this video and start tinkering.
Thank you Adnan! Yes I appreciate the feedback! All of my code are on GitHub (GitHub.com/onlyphantom) and I’ll make sure I link to them in my video descriptions for upcoming videos on the channel. Thank you!
Hey Samul, can you explain to me why the input and output are apparently switched in the torchviz graph? For example, your first linear layer is in your code as (784, 512) but is shown in the graph as (512,784). Thanks again, keep killing it!
Torchviz generates the graph using a backward pass, so these boxes are representative of the operation during the back-propagation. That’s at least how I reason about it, I would like to dig into it some more and find a more definitive explanation.
Thanks for the video Sam, this was helpful! I might recommend making these files more easy to find? It would be really useful to me if I could just get the file in this video and start tinkering.
Thank you Adnan!
Yes I appreciate the feedback! All of my code are on GitHub (GitHub.com/onlyphantom) and I’ll make sure I link to them in my video descriptions for upcoming videos on the channel. Thank you!
Hey Samul, can you explain to me why the input and output are apparently switched in the torchviz graph? For example, your first linear layer is in your code as (784, 512) but is shown in the graph as (512,784). Thanks again, keep killing it!
Torchviz generates the graph using a backward pass, so these boxes are representative of the operation during the back-propagation. That’s at least how I reason about it, I would like to dig into it some more and find a more definitive explanation.