MiDaS
MiDaS copied to clipboard
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
Issue converting the pytorch model to onnx with the attached script ![image](https://github.com/isl-org/MiDaS/assets/33397127/d50b72ac-54c5-47b0-9b8f-336fc04ec1bc) [pt_to_onnx.py.gz](https://github.com/isl-org/MiDaS/files/12707028/pt_to_onnx.py.gz)
# Issue: When creating ONNX file or Pytorch JIT trace, this utils file throws a type error, as the `torch.Size()` function expects an array of ints not torch tensors. #...
Getting this error while building the ros package, `[ 50%] Building CXX object midas_cpp/CMakeFiles/midas_cpp.dir/src/main.cpp.o [100%] Linking CXX executable midas_cpp /usr/bin/ld: warning: libopencv_imgcodecs.so.4.2, needed by /opt/ros/noetic/lib/libcv_bridge.so, may conflict with libopencv_imgcodecs.so.408 /usr/bin/ld:...
RuntimeError: Error(s) in loading state_dict for MidasNet_preprocessing:
Hi, I wonder how you managed to fit batch size 24 of your 48 GB GPU. Did you use .half() conversion for model and training data during training?
This is a great project, when I use the video input, the depth picture is flickering badly, will the next version fix it? Thank you so much~
This is a slightly tweaked version of https://github.com/isl-org/MiDaS/pull/234 @ranftlr could you please merge this?
Hi @thias15 @ranftlr i followed the step and i am able to run till midas node only as soon as i am running ./run_talker_listener_test.sh i am getting an error i...
Hello, is the depth generated through utils.py the inverse depth? Does it have units?
### Torch Compatibility We're working with the [latest nightly version](https://download.pytorch.org/whl/nightly/torch/) of torch. They seem to have added type asserts to interpolate [(this commit)](https://github.com/pytorch/pytorch/commit/6bda97e2c16fb35f743ff3fe292782d7ee082877). This causes a runtime error because the...