What is the Inception module?
mediumAnswer
- Multi-branch block that applies 1x1, 3x3, 5x5 convolutions and 3x3 max pool in parallel, concatenates the outputs along channels.
- Each branch captures features at a different scale. 1x1 bottlenecks reduce cost.
- Also introduces auxiliary classifiers at intermediate depths for training deep nets.
- GoogLeNet (Inception v1) won ImageNet 2014 with 22 layers and 6M params — 12x smaller than VGG-16.
Check yourself — multiple choice
- Single-branch conv only
- Multi-scale parallel branches (1x1, 3x3, 5x5, pool) with 1x1 bottlenecks — smaller than VGG at similar accuracy
- Same as ResNet
- No pooling used
Inception: parallel multi-scale conv branches with 1x1 bottlenecks.
#architectures#computer-vision
Practise Deep Learning
214 interview questions in this topic.