Serdar Dedebas·Jul 1DenseNet: The Network Where No Layer Forgets AnotherWhen I wrote about ResNet, one idea sat at the center of it: by adding a layer’s input back to its output (the residual connection)…
Serdar Dedebas·Jun 27ConvNeXt: A ConvNet Wakes Up in the 2020sWhen Swin Transformer arrived, there was a feeling in the air: the future of computer vision belonged to attention, and convolutions were…
Serdar Dedebas·Jun 26AlexNet: The Architecture That Started the Deep Learning RevolutionAlmost everything we talk about today — Vision Transformers, ResNet, YOLO, segmentation models, even the giant networks that generate…
Serdar Dedebas·Jun 18ResNet and EfficientNet: Two Ideas That Shaped Modern Computer VisionIf you have ever fine-tuned a model for image classification, run an object detector, or pulled a “pretrained backbone” off the shelf…
Serdar Dedebas·Jun 17You Only Look Once: How One Idea Taught Machines to See in Real TimeA friendly tour of YOLO — what it is, how it works, and why it quietly powers everything from self-driving cars to the camera that counts…
Serdar Dedebas·Jun 14Visualizing Model Training in PyTorch with TensorBoardAccuracy and Loss curves for train and test in the TensorBoard dashboard.