Hi @nkirukauzuegbunam, you need the output of the previous layer to match with the input of the following layer to be able to connect the two. This is facilitated by PyTorch.sequential. This way, the information flows smoothly through the backbone.
Hope this helps,
Maria
Thank you for the clarification
In case anybody missed this announcement: 📢 No session today & new time starting next week
Thanks for sharing the link!
Hey good people. Following the Discussion of ResNets by @amanarora I made a blog post going over the paper.
I try to replicate some of the experiments in the paper. Hope you will enjoy it
I have implemented ResNet from scratch in pytorch and posted it as kaggle kernel.
It currently achieves 76% accuracy, I will be tuning it further.
RestNet from Scratch in PyTorch | Kaggle
Thanks @amanarora for your video series.