Flame
Flame
I have this error when run, how could I find compatible pytorch? Exception: Installed CUDA version 12.3 does not match the version torch was compiled with 12.1, unable to compile...
Hi, Do you know why most of the label of totalsegmentator dataset is null? Do you have other source to download this dataset?
Hello, Author, Your paper is very nice, thanks for sharing. I have a confusion is that I can't find which part of the codes shows the knowledge distillation.
Hi Author, Thank you for sharing this project and for your kindness for answering my previous questions. I have some of questions want to ask about training: 1. What is...
Hi Author, 1. Do you use the megadepth dataset from 0000 to 5014 as training set like the 1st and 2nd images show? 2.When prep_info's corresponding Undistorted_sfm has both dense0...
Hi, Author, Thank you for the sharing. I am confused about why you use 5 different resolutions and the same convolutional network. And why you choose this convolutional network architecture?
Hi Author, Thanks for sharing. Have you ever tried the performance of using tiny dino in the encoder part?
Hi Author, thank you for the wonderful work. Could you also explain what each line of pairs.txt meaning? It isn't easy to understand the dataset without the documentation, especially for...
Hi, Author, I keep getting this error after quantize the model: Traceback (most recent call last): File "/home/my/roma_quant/experiments/quant.py", line 145, in test_mega1500(model, "quant") File "/home/my/roma_quant/experiments/quant.py", line 49, in test_mega1500 mega1500_results...
Hi Author. Thank you for the great work at first. I get a issue when training your pretrained model on megadepth, I find the loss is negative.  Here's the...