litingfeng

How to train on custom datasets?

9

Hi, Thanks for sharing the code. I was wondering if you could also share the instruction on how to train on custom datasets. Since I've noticed that you modified the...

What does self.rgb_lines = list(lines) * 10 mean?

1

Hi, Thank you for your great work. While I want to apply this method on my custom data, I found this line in ucf101.py. Why do you multiply 10 here?...

Question of tracking the untrackable

24

Hi, I just read the paper _Tracking The Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies_ and I have a question which I hope you can give me some...

Color saturation?

1

Not sure if I should call the problem as color saturation. In my generated images, I found out there's some pixel chunks, like the black area in the image below....

Why is dim_x set to 7 in KalmanFilter

3

Hi, Thanks for your great work. I was trying to understand the parameter here in this line: `self.kf = KalmanFilter(dim_x=7, dim_z=4)` From the document [here](https://readthedocs.org/projects/filterpy/downloads/pdf/latest/), `dim_x` means > Number of...

Use dali to train tinyimagenet does not reduce iterate time

1

Hi, I modified the file imagenet.py to train tiny-imagenet. I have organized the directories as specified in [issues#4](https://github.com/tanglang96/DataLoaders_DALI/issues/4#issuecomment-521075496). But the iterate time does not decrease too much, even slower( see...

with 11G memory still "Check failed: error == cudaSuccess (2 vs. 0) out of memory"

7

I have a K40 with >11G memory, but when I run `demo_LocNet_object_detection_pipeline`, it reminds me Check failed: error == cudaSuccess (2 vs. 0) out of memory. I thought 11G is...

I started using this tool last year. At first it was relatively stable, only randomly dropping off once per week. But it's becoming more and more annoying. The connection error...