Hou Lin Jie

upsample problem

1

Can deconv replace bilinear upsample?

can the method reconstruction panoramic image taken by mobile phone

2

can the LayoutNet reconstruction panoramic image taken by mobile phone?

Is there plans to publish DDAD15M datasets?

Why is same metrices to use resnet50 and regnet1.6gf as backbone with input size 896x1600 get same mAP 0.40?

Why to compute depth predict resultt is different from your paper ablation experiment?

3

`def safe_log10(x, eps=1e-10): result = np.where(x > eps, x, -10) np.log10(result, out=result, where=result > 0) return result def safe_log(x, eps=1e-5): return np.log(x+eps) def calculate(gt, pred): if gt.shape[0] == 0: return...

How to parse depth predict reuslt and to evaluate SILog, Abs Rel metrices?

1

Now, i get a tensor with downsample 16 times and use softmax to classify , How to reproduce the depth value metrices and to parse depth predict reuslt?

some a fews problem about compute depth details

2

`self.depth_channels = int( (self.dbound[1] - self.dbound[0]) / self.dbound[2]) ` 1. why is depth channels setting 'd_bound': [2.0, 58.0, 0.5] to compute channels is 112 ? 2. https://github.com/Megvii-BaseDetection/BEVDepth/blob/main/exps/bev_depth_lss_r50_256x704_128x128_24e.py#L271 Why to multiply...

How to train only a camera input with cam_front?

2

It's only change to the follow setting? `'cams': [ 'CAM_FRONT', ], 'Ncams': 1,`