-
Dear authors,
Thank you for opensourcing your work. I have quick questions about ORE application that needed clarification:
- Have you used BOTH mavl and RPN pseudolables during training? Or defa…
-
Hi, thanks for providing this model. I'm struggling with replicating the results using the files provided in the repository. Some of the paths do not seem to exist (e.g. the pseudo-labels), and the fi…
-
## Detailed Description
When choosing PV sytesm for a example, option to only choose the closest ones
## Context
if there are 1000 system in the system, and we want to only get 16 systems, mayb…
-
hey! cool stuff. im currently working on a similar system. what about repeating the process after the new weight is trained? to kinda keep getting better weights? any thoughts?
-
I have been reading up on continuing training on a custom dataset. I have a dataset that is about 50,000 images and training on these images is great, but takes quite a long while. So, I want to inter…
-
Thank you for your great work.
In the README, the contents are about having training target domain data on hand. But currently I am working on a project that it is restricted to use any labels from…
-
Hi,
I am wondering if you could elaborate on your top-K pseudolabelling scheme. Mainly I am wondering, if an image is in the top-K for multiple classes, does it appear in the dataset multiple times…
-
command line
./darknet detector demo data/obj.data cfg/yolov3-tiny.cfg /home/gordonlin/yolov3tiny/yolov3-tiny_last.weights "nvarguscamerasrc ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)7…
-
I'm trying to train a model similar to the noisy student approach and they have a batch size ratio between GT and pseudo Labels. Is there a simple way to take more images from a certain folder when lo…
-
Hi,
I am trying to use your algorithm using another dataset. After few epochs, when I tried to update the pseudo labels, I got this message :
```
Traceback (most recent call last):
File "Ps…