You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
How did you set the hyperparameter when training the baseline res50 model? I apply your method to SSD and it works. But in faster-rcnn case, I replace the vgg in your code with pretrained resnet50 and distill it with a resnet101 model on VOC2007 for 7 epoch, batch-size 1, 0.001 lr decay 1/10 at epoch 5. The final mAP of res50 model is 72.2 which is close to your paper. But without kd, the mAP can reach 74.0.
In your experiment using res50h model, do you use image-net pretrained weights or randomly initialized weights?
The text was updated successfully, but these errors were encountered: