那泼猴
那泼猴
我根据https://aistudio.baidu.com/aistudio/projectdetail/2250674?channelType=0&channel=0复现了BMN网络,可以看出BMN几乎把整个视频从头到尾都标记成了一个动作段,这样相当于什么都没标啊,能不能标的颗粒度更小一些?
Hi authors, Will we release it?
Please see the command and the output: (yolact_edge) cvteam@guest:~/yolact_edge$ python3 eval.py --trained_model=./weights/yolact_edge_mobilenetv2_54_800000.pth --score_threshold=0.3 --top_k=100 --image=ped.png:test.png Config not specified. Parsed yolact_edge_mobilenetv2_config from the file name. [01/24 19:44:23 yolact.eval]: Loading model... Traceback...
Hi author, please see the code in line 27: model_urls = { 'resnet50': '../libs/model_weights/TSM_imagenet_resent50.pth', 'resnet50_gated': '../libs/model_weights/TSM_imagenet_resent50.pth', } Why resnet50 and resnet50_gated point to the same place?
Hi author, there are too many download links from https://davischallenge.org Can you please point out which one do we use?
Hi author, Do you have any pretrained model with spectral normalization removed?
Hi author, It is pretty hard to train the network from train_git.py. Can you please give us a howto document or release the entire training code? Thanks!
Hi author, Seems no YouTube-VOS download link from https://competitions.codalab.org/competitions/19544 and too many DAVIS download links from https://davischallenge.org/davis2017/code.html Can you please give us a concrete hint about it?
Hi authors, If yes, can you show me some demo code for such a downstream task?
兄弟,你好: 不好意思在这开这个issue,看了你的博文:http://www.seeprettyface.com/research_notes_page3.html#intership 想试试训练OPN,无奈loss降不下去,能不能帮忙看看。。。