Phong Nguyen Ha

@breuckelen for me I can only train 4 frame sequence using the original code. My computer only have 32 GB of RAM. One more question: should I increase the number...

@breuckelen Actually I have implemented a new dataloader to load a subset of rays per iteration. Doing so significantly reduced the amount of RAM required to start training. I will...

Hey guys, can we stop asking the team to release the code. I think they know we are all waiting but we need to give them some time to polish...

A very quick fix for me is to change this [line](https://github.com/dcharatan/flowmap/blob/19ac72b78d010220bd9487553db4fb463ab317d4/flowmap/tracking/track_predictor_cotracker.py#L23) of code to the new version of CoTracker. `self.tracker = torch.hub.load("facebookresearch/co-tracker", "cotracker2")`

@dcharatan Hmm, so I would need to manually download the weight of the V1 CoTracker here and load it to reproduce your results?

Hi, I wonder how can I do that with the current codebase ?

> @phongnhhn92 @chenusc11 could you send a quick fix to that code? I am sorry for slow reply. I think @chenusc11 found the solution. I didnt notice that you combine...

Hello guys, I hate to do this but I have to reopen the issue again. This is the code that I copy and adapt from the example: ``` import torch...

I am afraid to tell that I made a mistake thinking the problem is solved. I thought just simply change the line as @chenusc11 would help but it turns out...

@mariannanovaes @isharaux Sorry, i cant :(