Open Guptajakala opened 3 years ago
Hi, thanks for the great repo! I'm interested in finetuning the model for my research and I'm trying to understand your implementation here: https://github.com/naver/r2d2/blob/740f6fb2a4372e1dae3b5b70903aefb6ba872124/tools/dataloader.py#L119
1) what is this line doing?
2) From the comments above, it says "applying a median filter" but I didn't see median filter afterwards. Is this comment deprecated?
3) https://github.com/naver/r2d2/blob/740f6fb2a4372e1dae3b5b70903aefb6ba872124/tools/dataloader.py#L145 Seems here you are doing some window selection based on best optical flow quality. Is this part necessary? Does it make big difference compared with random sampling a valid window inside the image region (without score comparison)?
Hi, thanks for the great repo! I'm interested in finetuning the model for my research and I'm trying to understand your implementation here: https://github.com/naver/r2d2/blob/740f6fb2a4372e1dae3b5b70903aefb6ba872124/tools/dataloader.py#L119
1) what is this line doing?
2) From the comments above, it says "applying a median filter" but I didn't see median filter afterwards. Is this comment deprecated?
3) https://github.com/naver/r2d2/blob/740f6fb2a4372e1dae3b5b70903aefb6ba872124/tools/dataloader.py#L145 Seems here you are doing some window selection based on best optical flow quality. Is this part necessary? Does it make big difference compared with random sampling a valid window inside the image region (without score comparison)?