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"
MIT License
4.25k
stars
597
forks
source link
What is the model type of the models available in the ONNX format in https://github.com/isl-org/MiDaS/tf ? #233
Hi,
I can see the in the tf/ folder there are two onnx files model-f6b98070.onnx and model-small.onnx but their name does not match to an of the models mentioned in dpt_beit_large_512, dpt_beit_large_384, dpt_beit_base_384, dpt_swin2_large_384, dpt_swin2_base_384, dpt_swin2_tiny_256, dpt_swin_large_384, dpt_next_vit_large_384, dpt_levit_224, dpt_large_384, dpt_hybrid_384, midas_v21_384, midas_v21_small_256, openvino_midas_v21_small_256.
Can you clarify what is the model type of those nets?
Best Regards