Analyse @giffmana's tweets
@giffmana
| 43,467 followers
Disagree. As soon as you throw sparsity in (and depthwise/tiny-group conv is a form of sparsity) FLOPs detach from reality.
That's why sparse nets are hard (https://t.co/CoiXNnEWC9), and EffNetV2 actually UNDOES a lot of depthwise.
EffNetV1 == MobileNetV3 == designed for CPU. https://t.co/tu1cAJ6O9u
That's why sparse nets are hard (https://t.co/CoiXNnEWC9), and EffNetV2 actually UNDOES a lot of depthwise.
EffNetV1 == MobileNetV3 == designed for CPU. https://t.co/tu1cAJ6O9u