-
In the process of data augmentation, I am trying to modify the image based on the corresponding mask. I need to get the background from the image, which requires knowing the foreground (mask) in advan…
-
Thank you for bringing us this great audio restoration project.
I'm training a vocal stem enhancement model on a single RTX 3090 in bfloat16 precision (which reduced the vram usage in half).
In th…
-
## 🚀 Feature
Nice project. Please add support to random rotation which can accept a `list degrees`-(0, 90, 180, 270, 360...) not only the `range degrees`, like range(-90, 90). If I miss something,…
-
- [x] Research about augmentation
- [x] Left/right movement
- [x] up/down movement
- [x] random rotation
- [x] flip left/right/up/down
- [x] random brightness
- [x] random zoom
- [x] Augmentation prot…
-
Record discussions here for convenience.
## 03-13
### Fields of papers
**P1**: ~~Text classificcation/aggregation & Semantic role labling~~Event exraction
**P2**: Data cleaning & Data augmen…
ZacBi updated
4 years ago
-
we need to decide the best way to do the data augmentation, this should be transform to a keras try? o we should use multithread procesing?
-
# Background
- 데이터셋의 증강 순서가 바뀌어 제대로된 데이터 증강 x
# To do
- [x] dataset 증강 순서 수정
-
Hi, my data set labels are unregular, where to modify the data preprocessing code?
The format of the label is like this:
-
I have a custom coco detectio dataset with images of variable size. To ensure every example seen by the model is presented at the same resolution I apply the T.FixedSizeCrop((SIZE, SIZE), pad_value…
-
The giraffe image in develop/guide/gluon/data_augmentation.html#Data-preproecessing looks incorrect.
New docs:
![2018-11-01_18-32-22](https://user-images.githubusercontent.com/5974205/47888956-88bb1…