search

anonymous47823493 / EagleEye

(ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
304 stars 68 forks source link

Question for full-size baseline model performance in paper's Table.4 and Table.5 #40

Closed dercaft closed 3 years ago

dercaft commented 3 years ago

Hello: What's your full-size baseline model performance in Table.4 and Table.5? In your paper, there is only compressed baseline model performance, eg. 0.75× ResNet-50's Acc 74.8% But in other works, they usually use full-size baseline model as a comparison. So I wondered what's your full-size baseline. Looking for your reply. Thank you.

Bowenwu1 commented 3 years ago

The acc of our full ResNet-50 is 77.2%. The acc of our full MobileNetV1 is 72.62%.

For details of our full models, you can refer to https://drive.google.com/drive/folders/1ENq4RuFey3J2iL-Lu1BZ9ToTYILpV9bC for full model checkpoints.