This repository was archived by the owner on Sep 21, 2025. It is now read-only.
This repository was archived by the owner on Sep 21, 2025. It is now read-only.
MODEL: Conv.1 - 3x3 Kernel, 32 filters, edge detection. #32
Take in the input frame, which will be a128 x 128 (RGB) image with 3 channels. Preprocessing by dataset will be applied (rotations, flipping, lighting, etc)
Stride: 1, Padding: "same", activation: ReLU, Output: 128x128x32