1. Home
  2. hussam.lawen
  3. mrT23/TResNet
  4. Build #80

mrT23 / TResNet » Build #80

Build Results

Dataset Image Classification on ImageNet

Image Classification on ImageNet

TOP 1 ACCURACY TOP 5 ACCURACY
SPEED
MODEL CODE PAPER
ε-REPR
CODE PAPER
ε-REPR
PAPER
TResNet-L
81.4% 81.4% 95.6% 95.6% 496.3
TResNet-L
(288-Mean-Max)
82.0% 81.4%
96.1% 95.6%
356.4
TResNet-L
(input=448)
83.8% 83.8% 96.7% -- 144.4
TResNet-M
80.7% 80.7% 94.8% 94.8% 507.5
TResNet-M
(288-Mean-Max)
81.6% 80.7%
95.4% 94.8%
410.9
TResNet-M
(input=288)
81.4% 80.7%
95.2% 94.8%
409.8
TResNet-M
(input=448)
83.2% 83.2% 96.2% -- 289.5
TResNet-XL
82.0% 82.0% 95.9% 95.9% 445.4
TResNet-XL
(288-Mean-Max)
82.8% 82.0%
96.3% 95.9%
256.5
TResNet-XL
(input=448)
84.3% 84.3% 96.9% -- 108.7