heyoeyo

The best approach may be to try using the [ZoeDepth](https://github.com/isl-org/ZoeDepth) models which are built to give metric distances as an output. Otherwise, if you know the range of the depth...

> Is there any way to extract the exact distance(in meters) of any pixel in the image? Metric depth models (like [ZoeDepth](https://github.com/isl-org/ZoeDepth)) attempt to do this. With relative depth models...

> If you know the real depth (meters) for 1 pixel, would it be enough to convert the rest of the depths to real distance too? Not quite, it's sort...

I'm not sure if there is a perfect way to count FLOPs. One option is to use some software that estimates the count from the model definition. Searching around, it...

The cutouts would just be a copy of the original image, where an alpha channel has been added and set to the (binary) segmentation mask. That way areas outside of...

Getting the cutouts to match the size of the object can be done by cropping the image. Again, it depends on how you're handling the image data, but in opencv...

Do you have a specific format in mind? I'm not familiar with any image formats that support non-rectangular boundaries. If you only need the shape and not the pixel data...

> what is the shape of your saved mask file? In the example, the mask is just being generated randomly and has a shape of (256,256), with no channels (or...

If you're using the amg.py script, then you might want to try using the `min_mask_region_area` flag and setting a large value. The idea being that if the minimum mask area...

For filtering out large masks, you can do something like: ```python masks = mask_generator.generate(image) # ... result from auto-mask generator max_mask_area = 10000 small_masks = list(filter(lambda m: m["area"] < max_mask_area,...