Dingchi Sun
Dingchi Sun
same here, any progress?
disp to depth with min and max depth using this code may be helpful def disp_to_depth(disp, min_depth, max_depth): """Convert network's sigmoid output into depth prediction The formula for this conversion...
with torch.no_grad():
有进展吗兄弟 我也是batchsize改不成
Any progress?
sorry, its been too long. I successfully transfered this model into onnx, by **changing some functions** in tensor and np convertor? Maybe? I remember u can see the **warning log**...
In report,MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation,5.Applications says that **ZoeD-M12- NK, incorporates a MiDaS v3.1 architecture with the BEiTL encoder with a newly-proposed metric...
Hello, 不知道我描述的你能不能理解（英文不咋滴）: PNG images can be set in many modes, uint8 contains 0-255 uint16 contains 0-65535 in some depth estimation dataloader, u can see that, during data pre-processing the nyu...
@uowei "單眼深度估計出來的結果應該都是相對深度"这句话的描述_对但没完全对_，在这些采用多数据集共同训练的模型出来之前，单目去估计绝对深度的时候多数采用的是估计出经过sigmoid后的(0,1)的相对深度，再和maxdepth（不同数据集不一样）相乘，所以之前有视为**绝对深度=相对深度*maxdepth**的工作（但其实这么描述不太准确，而且泛化性能明显不够，因为不同数据集有不同的先验条件）。 比如bins的方法，adabins原文里提到D = (dmin, dmax) into N bins.This interval is fixed for **a given dataset and is determined by dataset specification or manually set to a reasonable range** 也是提前设定好的，比如只是把100m切成很多份，...