-
Thanks for your nice work!
But when I retrained your searched architecture with default DARTS settings, I got the following results (the same architecture with 8 runs):
97.379997
97.309998
97.3999…
-
Since the original code does not work well with Pytorch 0.4 or later, regard this concern,
I reimplement the CNN part that supports the latest Pytorch, and the code is available at
https://github.co…
-
- PyTorch-Forecasting version: 0.9.2
- PyTorch version: 1.10.2
- Python version: 3.8
- Operating System: Ubuntu
Hi there!
Thanks for this great package. I have a problem with multiple timeser…
-
## 📚 Documentation
i want to use dp with NAS, when i use the pre-trained DARTS model , ModuleValidator.fix() function does't work! anyone meet this problem?
-
In the discord server, a while ago we mentioned the possibility of generating CV splits based on time intervals (e.g. the first day of the month or week). This might be useful for financial settings e…
-
-
**Is your feature request related to a current problem? Please describe.**
I need to be able to robustly backtest any ForecastingModel so I can he a valid view how the model performs over time. As th…
-
Hello!
I find you use historical_forecasts() in WTransformer.py file to calculate metrics; while use predict() in TestAllModel.py. What`s the difference between historical_forecasts() and predic…
-
# Reference
- 07/2020 [MS-NAS: Multi-Scale Neural Architecture Search for Medical Image Segmentation](https://arxiv.org/abs/2007.06151)
- [MS-NAS：用于医学图像分割的多尺度神经网络架构搜索](https://zhuanlan.zhihu.com/p/1…
-
Traceback (most recent call last):
File "train_search.py", line 211, in
main()
File "train_search.py", line 136, in main
train_acc, train_obj = train(train_queue, valid_queue, model,…