-
Dear Chaoqi, @chaoqichen
Thanks for your nice work of HTCN published in CVPR 2020! I found the paper quite interesting and your clear and compact illustrations inspired me a lot.
I use the code y…
-
## 一言でいうと
ラベルなし別データセットへのDomain Adaptionのために、Pseudo-Labelling を使った、複数IterationのTrainingをしたい。
Bayesian CNN の出力するUncertaintyを（ピクセル間）lossの重みとする（k-1 round目でのUncertaintyが、k round目のtrain時に使用される）。
Bayesian…
-
# Interesting papers
- [Davison 2018 - FutureMapping: The Computational Structure of Spatial AI Systems](https://arxiv.org/abs/1803.11288)
- Imperial College London의 Dyson Robotics Lab 교수님이신 A…
-
Running zsm_my_video.sh. No matter what I do, I keep getting out of memory errors. I'm using an RTX 2060 with 16GB of system RAM and 6GB of dedicated GPU RAM. I'm running against a 1 second clip from …
erdog updated
3 years ago
-
torch.FatalError: invalid argument 5: 4D weight tensor (nOutputPlane,nInputPlane,kH,kW) expected, but got: (null) at /mnt/ssd0/project/ytian21/videoSR/DCN/src/deform_conv_cuda.c:15
-
Hi everyone,
Thanks for such a great project. I found two error cases when I tried to process a PDF (see the attachment) by python client. The command is processFulltextDocument.
I tried both …
-
Hi
I got the deepfasion dataset, but the structure of the image folder is wrong.
where can I get the image which have 'lbl' or 'val' image folder name
-
# Reference
**paper**
- 09/2018 [Searching for Efficient Multi-Scale Architectures for Dense Image Prediction](https://arxiv.org/abs/1809.04184)
- 10/2018 [Fast Neural Architecture Search of Compac…
-
Hi, and thanks for making this code available!
I have a moCap system that outputs 3D points as joint positions in world space.
What I need to do is 'solve' these positions onto a skeleton, eg: Creat…
-
How to test my own file.mp4? Thank you !