toby comments

Results 7 comments of


                                            toby

It's different with the standard SegNet

yes, i'd like to do that. i have rewrited segnet.i will send it by my pull.

It's different with the standard SegNet

Hi,there just one pooling at each dec. could you tell me the your found on detail.

It's different with the standard SegNet

layer4 is maxpool, it is used later in code in order to get max-index.

it's too slow!

I think the 'realtime' means that it's faster than hourglass!

bevformer-base AP=0, i change the encoder layernum from 6 to 3, i got the AP=0 result

Thanks for you replay! i will show my some modified details. - bevformer.py: we don't use the prev_bev, same time we change the video_test_mode=False when test. ` len_queue = img.size(1)...

bevformer-base AP=0, i change the encoder layernum from 6 to 3, i got the AP=0 result

2022-07-13 07:48:49,431 - mmdet - INFO - Epoch [2][50/3517] lr: 1.991e-04, eta: 2 days, 6:35:14, time: 2.612, data_time: 0.523, memory: 18492, loss_cls: 0.0685, loss_bbox: 0.2451, d0.loss_cls: 0.0697, d0.loss_bbox: 0.0798, d1.loss_cls:...

bevformer-base AP=0, i change the encoder layernum from 6 to 3, i got the AP=0 result

i didn't load the pretrained model and i didn't remove the frozen_stages setting! -_-!