mega.pytorch
mega.pytorch copied to clipboard
Scalsol
Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020
想问一下，我想使用FPN，修改了以下三个地方：1.rpn.use_fpn=true；2.anchor stride 个数和size一样多；3.backbone改为R-50-FPN.请问修改这三个地方够吗？
``mega_core.trainer ERROR: Iteration=4 || Image names used for training ('train/ILSVRC2015_VID_train_0003/ILSVRC2015_train_00839000/000255',) || targets Length=[0]`` (I have modified the error log infor to print the image file name) In `self.filter_annotation()`, `class VIDMEGADataset`,...
Hello! I am interested in the results of your top performance model, i.e. ResNetXt-101. Are you planning to release its weights and evaluation scripts? Thanks in advance!
Hi! When performing object detection inference, I would like to return all the class confidence vectors, not only the best score/class for each bbox. Can you provide me some intuition...
Hi, 我想问一下，预测时，CPU使使用率非常高，这个问题怎么去解决. 貌似在数据预处理的时候，CPU全部的核全部占满了，超额了到达：1000-2000. 
Due to some reasons, I cannot install the full apex and only install the "Python-only build" version. Then I met the RuntimeError as below.  How can I run the...
Dear Author, Thanks for your sharing. I tried to make a demo of inference on an image folder with the online setting, but I'm a little confused about how to...
Thank you so much for your incredible work! For a paper I am writing about possible applications of object detection algorithms I am in need of the distribution of AP...
