-
### System information
- **OS version/distro**: Windows 10
- **.NET Version (eg., dotnet --info)**:
### Issue
- **What did you do?**
I've trained a LGB-model from the python lightgbm pac…
-
## Feature request
Create an example of how custom training loops and dataloaders should be done with this library. Alternatively or additionally make helper methods that are designed to make cus…
-
**System information**
- Have I written custom code (as opposed to using a stock example script provided in TensorFlow): yes
- OS Platform and Distribution: MacOS 10.15.1
- TensorFlow installed fro…
-
If a user closes the current classifier widget window and initializes a fresh classifier, that doesn't work.
Multiple issues:
- What about the pre-existing selection & prediction layers?
- Keybind…
-
### Proposal Summary
When loading ground truth and netwrok prediciton, it would be nice to be able to directly define colors at that moment.
Example, I want all my ground truth in green and my pr…
joihn updated
2 years ago
-
# Vaex First
Typo: "Vaex is an open-soruce..."
Fix: "Vaex is an open-source"
Typo: "...to allow the extreme flexibility for advance pipeline solutions..."
Fix: "...to allow the extreme flexibili…
-
**Describe your question.**
I am research in the ADMET prediction. The work of TDC is fantastic. In the tdc.single_pred, when I have trained model, how I use the .pt file to predict a strange…
-
Well, let me start with thanking you with this great work. It's awesome.
If, for example, I have a 20s-long video where several actions take place for 4-5s each. Is the model capable of predicting …
-
## 앙상블 방안
#### 오늘(20.03.02.) 회의에서 나온 다양한 의견들을 바탕으로 이번주 실험을 하면서 고민해야 하는 점을 정리해서 올립니다.
#### 1. 토크나이저가 다른 두 모델 (담당 : 재우, 영민)
- 토크나이저가 다르면, 학습 데이터를 생성하는 과정에서 max_len이 달라집니다. 따라서 토크나이징된 텍스트의 길이가 다른 경우,…
-
Currently, it seems impossible to just get a list of bounding boxes from the predictions.
```python
img = np.array(Image.open("..."))
infer_ds = Dataset.from_images([img], valid_tfms, class_map…