-
Hi, Haoyi. Thanks for your great work. Recently, I find that PonderV2 gets a better performance of semantic segmentation on ScanNet++. I also have tried to use the official toolkit to process the data…
-
Had someone show me this error on their dataset and I was able to duplicate it with some existing data in qiita. Just trying to run a random forest sample classifier on one categorical data with a non…
-
### Ticket Contents
## Protean Overview
Protean eGov Technologies Limited provides IT services. The Company offers citizen services, e-governance solutions, system integration, business process re…
-
## 🐛 Bug
### To Reproduce
Steps to reproduce the behavior:
1. In Kaggle notebook,
2. Run `!pip install -U LightAutoML`
3. Minor installation error msg.
ERROR: pip's dependency resolve…
-
[Improved Regularization of Convolutional Neural Networks with Cutout](https://arxiv.org/abs/1708.04552) proposes a simple and effective method for regularization. I think it would fit greatly in the …
-
### Bug Description
INFO:tensorflow:Reloading Oracle from existing project ./image_classifier/oracle.json
Search: Running Trial #1
Hyperparameter |Value |Best Value So Far
i…
-
Hi, while trying to use the following snippet:
```python
import texar.torch as tx
from texar.torch.run import *
# (1) Modeling
class BERTGPT2Model(nn.Module):
"""An encoder-decoder model …
-
**Describe the issue**:
I'm trying to use nni on colab as describe in the book "Time Series Forecasting Using Deep Learning" by Gridin. However all my trials fail and I can't find the logs to trouble…
-
Dear authors,
Thank you very much for this great work!!
I have a question about the 'mult' parameter in the library.
Is this a hyperparameter which is described in the u-muP paper?
If yes, sho…
-
Properly train the model:
- Find appropriate dataset for train, test, validation
- Mix Brush/Unipen ? Separate writer IDs for test and valid to have unseen data ?
- Make hyper-parameter search on…