DPT
DPT copied to clipboard
isl-org
Dense Prediction Transformers
Hi, As you can observe from the following stacktrace, we need to also provide pillow in the environment. Traceback (most recent call last): File "run_segmentation.py", line 11, in import util.io...
This PR implements ONNX conversion scripts and scripts to run the resulting models on monodepth and segmentation tasks. Furthermore fixes from #42 are incorporated. The converted weights are available [here](https://github.com/timmh/DPT/releases/tag/onnx_v0.1)...
Hi i have a question. I wanted to know what is the units of the output depth map given. For an image, using kitti pretrained,i obtain for a determined pixel...
Hi, I want to run inference with the MiDaS model (DPT-large) on large images (2k, 4k, etc.). My GPU memory maxes out just before reaching the 2k image size. For...
You haven't released the training and evaluation code for Monodepth and Semantic Segmentation tasks. If you can provide your training and evaluation code then that will be very useful for...
Hi, Do you finetune on kitti using the sparse GT as it is and interpolate predictions only for visualization or are the depth maps interpolated for training itself too (seemingly...
I am trying to convert the DPT_Scriptable model to a coreML model but am unable to due to this error. `RuntimeError: NYI: Named tensors are not supported with the tracer`...
Hello, First of all, I would like to say thank you for your work. I would like to evaluate the MiDas v21 model on NYU Depth v2 dataset. Based on...
I've seen few issues where people were trying to train the network, but cant find any training code. Is there anything available? I'm interested in loss function, pipeline for data...
