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
4.27k
stars
599
forks
source link
device "mps" for Apple silicon - strange output #184
I've tried to run MiDaS on Apple silicon with pytorch nightly with mps (metal performance shader) support.
I've change two lines of code to get this working:
28 - device = torch.device("cuda" if torch.cuda.is_available() else "mps")
and
127 - mode="bilinear",
The change to "bilinear" is necessary because bicubic is not supported currently for the M1 native implementation. Influence on output quality is neglectable in my experience (I did a few comparing tests on "CPU" with only this parameter changed)
This way I could speed up inference by a whopping factor of 6. But: Output quality detoriates to not-usable. I've got virtually no experience with python and pytorch - I'm basically a hobbyist creator and dad who wants to have a depth map on selected gopro footage of his son to fake depth of field into it. So i do not know where to look at.
Legacy Midas V2 seems to work okay and delivers the same output on CPU and MPS:
CPU
MPS
DPT however, output becomes unusable with mps:
MPS
duckheada
commented
11 months ago
I've tried to run MiDaS on Apple silicon with pytorch nightly with mps (metal performance shader) support.
I've change two lines of code to get this working: 28 -
device = torch.device("cuda" if torch.cuda.is_available() else "mps")and 127 -mode="bilinear",The change to "bilinear" is necessary because bicubic is not supported currently for the M1 native implementation. Influence on output quality is neglectable in my experience (I did a few comparing tests on "CPU" with only this parameter changed)
This way I could speed up inference by a whopping factor of 6. But: Output quality detoriates to not-usable. I've got virtually no experience with python and pytorch - I'm basically a hobbyist creator and dad who wants to have a depth map on selected gopro footage of his son to fake depth of field into it. So i do not know where to look at.
Legacy Midas V2 seems to work okay and delivers the same output on CPU and MPS:
CPU
MPS
DPT however, output becomes unusable with mps:
MPS
Any ideas? Can someone give me a hint?