iacopocurti

I am willing to use mask2former achitecture with beit-adapter for a binary segmentation task, in which i need to recognize lanes in the image, classifying anything else as background. Should...

Hi, thank you for your amazing work! I have a question regarding the number of iteration in the following scenario. I have a gpu with 12 gigs, I have managed...

After Freezing the Vit backbone how many iterations are supposed to be trained?

1

Hi, thank you for your fantastic work. I am working with Mask2former framework, and I am training from scratch according to the Mapillary case. The only difference with your framework...

Utilization on windows 10

4

Is it possible to use this repo with windows 10?

Traceback (most recent call last): File "setup.py", line 100, in setup( File "/usr/local/envs/lanedet/lib/python3.8/site-packages/setuptools/__init__.py", line 107, in setup return distutils.core.setup(**attrs) File "/usr/local/envs/lanedet/lib/python3.8/site-packages/setuptools/_distutils/core.py", line 185, in setup return run_commands(dist) File "/usr/local/envs/lanedet/lib/python3.8/site-packages/setuptools/_distutils/core.py", line...

Inference

1

Is there a script like in the lanedet repository, which allows to use the model on new images?

Good morning, thank you for sharing your work. I would like to know how you implement the vectorization of the lane points or which methods you used to derive yours...

Is there a way to extract the number of parameters of the functa framework?

Hi, thank you for your extraordinary work, I don't understand according to which rule do you set the drop path rate? Sometimes in smaller model is 0.1 and sometimes in...

Thank you for your work, I am having some problems with your dataset, I don't unferstand why the number of images cied in the file enityseg_semseg_ytain.txt are fdifferent from the...