DeepForgeby svx

0/5730 solved

← All collections

ResNet & Residual Blocks

Residual connections and the convolutional blocks that carry them. Skip and bottleneck shapes, depthwise convolutions, batch-norm folding, and the parameter counts behind ResNet-style architectures.

12 problems

Your progress

0/12 · 0%

Continue collection · Zero Padding

Problems

Zero Padding
cv-005Computer Vision
Easy
Global Average Pooling
cv-012Computer Vision
Easy
Conv Parameter Count
cv-087Computer Vision
Easy
Residual Output Shape
cv-225Computer Vision
Easy
U-Net Skip Connection Shape
dl-231Deep Learning
Easy
Depthwise Conv Output
cv-238Computer Vision
Medium
Group Conv Output
cv-239Computer Vision
Medium
BatchNorm Fold into Weights
cv-240Computer Vision
Medium
Bottleneck Block Param Count
cv-243Computer Vision
Medium
Inverted Residual Expansion
cv-244Computer Vision
Medium
Conv+ReLU Fusion
cv-242Computer Vision
Medium
BatchNorm Fold Bias
cv-241Computer Vision
Medium