-
-
## ๐คท ์์
ํ ๊ธฐ๋ฅ ์๊ฐ
> ์์
ํ ๊ธฐ๋ฅ์ ๋ํด ๊ฐ๋ตํ ์๊ฐ
Pseudo labeling & TTA (Data leakage X)
## ๐จ ์์ธ ์์
๋ด์ฉ
> ์์ธ ๋ด์ฉ ์ด๊ฑฐ
- [x] To-do 1 Pseudo labeling
- [x] To-do 2 TTA
- [ ] To-do 3
## ๐ ์ฐธ๊ณ ์ฌํญ
> ์ฐธ๊ณ ์ฌํญ ์ ๋ฆฌ
์๋ฒโฆ
-
I would like to fine-tune the model towards the data that I will be feeding it. My pipeline would be to binarize the images using sbb_binarize, then manually edit them to be high-quality ground-truth,โฆ
-
Hello there! Is it really possible to improve the quality of detection? I have a trained model, the height and width is now 448x448 (I do not do it anymore, because FPS is decreasing). Detects not verโฆ
-
Hi, I want to fine tune a model with my custom data corpus so that it's embedding store in the model. I have dataset similar to sts dataset. but instead of giving score I Just want to train my model wโฆ
-
Hello, I downloaded the corresponding dataset according to the readme, but encountered an issue while running the train.exe file. Could you please provide specific files that need to be stored in the โฆ
-
### What is the problem this feature will solve?
semi-supervised object detection for mmyolo.
### What is the feature you are proposing to solve the problem?
Hello Open MMLab team, thank you for deโฆ
-
## Background
- swin base ๋ชจ๋ธ๋ก๋ง ์์๋ธ์ ํด๋ณธ ๊ฒฐ๊ณผ, LB ์ ์๊ฐ 0.005~0.01 ์ ๋๋ฐ์ ์ค๋ฅด์ง ์์์. (pspnet, upernet, PAN)
- ๋ฐฑ๋ณธ์ ๋ค์์ฑ์ ๋์ด๋ฉด ์์๋ธ ํจ๊ณผ๋ฅผ ๋ ๋์ด์ฌ๋ฆด ์ ์์ ๊ฒ ๊ฐ์.
## Content
- hrnet + ocr (mmseg). epoch 50
- validโฆ
-
Is it correct for me to understand this way?
You are implementing kmeans on stm32, through kmeans, the data received by the sensor is divided into several categories and labeled, and after a certain โฆ
-
_Please make sure to close the issue once you consider it as solved_
_Please use screenshots only when you cannot copy-paste the object, e.g. for figures or maps_
**Error and context**
The error โฆ