Qi HE
the squre is not in the right place, and it should be like this: wrong: $$ \begin{align}-\frac{(z-x)^2}{2\sigma^2_{GPS}}-\frac{(x-x_{init})^2}{18\sigma^2_{GPS}} &= -\frac{9(z-x)^2+(x-x_{init})^2}{18\sigma^2_{GPS}} \\ &= -\frac{9(z^2-2zx+x^2)+(x^2-2xx_{init}+x_{init}^2)}{18\sigma^2_{GPS}} \\ &= -\frac{{9z^2+x_{init}^2}+10x^2-2xx_{init}-18zx}{18\sigma^2_{GPS}} \\ &= -\frac{{9z^2+x_{init}^2}+10x^2-2(x_{init}+9z)x}{18\sigma^2_{GPS}} \\ &=...
Hi, I find the latest configuration file from mmdetection official released version is different from here. Which one is better in your experiment? here: https://github.com/hustvl/QueryInst/blob/a10cca02ce6eabb12ca537b821535c2663b9c835/configs/queryinst/queryinst_r50_fpn_1x_coco.py#L121 or official released version from...
I have trained TSD on the Docker. - baseline: tsd faster rcnn: - dataset: stanford cars. envs: - cuda=10.1 - pytorch=1.3.0 - mmcv=0.4.3 My training log is as below, I...
Which RL algorithm do you used to train? Can you also provide the corresponding YAML?
Hi. As I carefully read about your paper and examples, I found the visual signal are not used in the given MLAgents. In addition, I found your settings for obtaining...
on https://github.com/hhb072/IntroVAE/blob/master/networks.py line 40 `output = self.relu2(self.bn2(torch.add(output,identity_data)))` I see the normal ResBlock code like this form: `output = self.relu2(torch.add(self.bn2(output),identity_data))` Why Add before batchNorm?
why i get "proxychains4" instead of "proxychains". and "proxychains4 git clone xxxx" alway fail!
"taking the re-projected z value as the keypoints' depth D_{ij}" is actually not what this paper does. I means "re-project" might not be the right word for this operation. It...
How do you organise the training, validation, and testing set for the synthetic Unity data set? Can you just provide more details?
The distance from light source to object surface are related to depth. Why not consider it in your light model?