semel1

Results 25 comments of semel1

Can't mange to get "image_size" to work. Tried -- image_size 216,384 as stated in the help (-h) "--image_size IMAGE_SIZE the image size, eg. [216,384]" - it trows an error: "test.py:...

The same problem with flickering when processing image sequence. It caused by producing inconsistent depth map. Such" collateral effect " makes calculated depth maps unusable in case of processing image...

It looks like solution here https://robust-cvd.github.io/. Waiting for code.

Here report from nviia-sm on Windows 10 and WSL2i: ![nvidia_smi](https://user-images.githubusercontent.com/53234248/175363615-a620d009-26be-47a0-b1b7-82b588c181be.png) Anyway comment out line 49 only and replace it with os.environ["CUDA_VISIBLE_DEVICES"]="0", throws an error: ``` File "main_IRT.py", line 50 os.environ["CUDA_VISIBLE_DEVICES"]...

I have the same issue: "You are using the mapping model without global restoration."

Google Colab throws an error: ``` /content/TCMonoDepth Run Video Depth Sample Initialize Device: cuda Creating model... Loading model path fail, model path does not exists. ```

It appears that Colab doesn't download _ckpt.pt.tar. So, you have to upload it manually.

I have same problem with Tesla V100-SXM2-16GB, RuntimeError: CUDA call failed (correlation_forward_cuda at correlation_cuda.cc:80). niuhuojian said that P100-PCIE-16GB works, unfortunately I can't specify which GPU should be used . The...