search

VDIGPKU / M2Det

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
MIT License
1.45k stars 318 forks source link

TUM #2

Closed Sun-Fan closed 5 years ago

Sun-Fan commented 5 years ago

hello, thanks for your paper. In your paper, you have used 8 Tums.I want to ask if this will cause the low fps. After all, there are many Convolution layers.Thanks!

muye5 commented 5 years ago

Both TUM and SFAM are a little complex，it doesn't make sense why this architecture could speed up so fast. Both the hourglass TUM and fully connection attention are not friendly to speed. Wait for the code.

qijiezhao commented 5 years ago

TUM is a Thinned U-shape Module, it is not as slow as you think. The parameters of A TUM is even less than a Conv layer 1024x3x3x1024. SFAM is also not as complex. First, concatenation; then implement SE attention for multi-scale features. Only 6 SE attentions. As a comparison, SE-ResNet101 have more and more SE attentions than ResNet101.

leo-XUKANG commented 5 years ago

i have tried it in darknet ,and where the network get deeper ,then the network will be slower,

HoracceFeng commented 5 years ago

@leo-XUKANG very interesting try. I am also curious why M2DET will have such fast speed. Would you share your code of M2DET in darknet?