Stride = 2 only for the first block of the entire ResNet
PavelShtykov opened this issue · comments
According to this row, ResNet is created only with one convolution with stride = 2:
Is it ok?
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
PavelShtykov opened this issue · comments
According to this row, ResNet is created only with one convolution with stride = 2:
Is it ok?