-
- [ ] Look into TorchMTL for safe build multi-task model
> - github: https://github.com/chrisby/torchMTL/blob/af1d05474fe78e67aeb7c5898770fbd464172039/torchmtl/model_builder.py#L86
> - tutorial: ht…
-
When will be the source code available for exploration?
-
-
### Context
We are working on learning how to use DSPy in the best way for our program. For each building block of DSPy, I'm creating subtasks to be tested on the pipeline.
### Subtasks
#### 0.…
-
- [ ] [Everything-of-Thoughts-XoT/README.md at main · microsoft/Everything-of-Thoughts-XoT](https://github.com/microsoft/Everything-of-Thoughts-XoT/blob/main/README.md?plain=1)
# Everything of Thou…
-
https://www.csie.ntu.edu.tw/~htlin/paper/doc/aaai15albl.pdf
Pool-based active learning is an important technique that helps reduce labeling efforts within a pool of unlabeled instances. Currently, …
leo-p updated
7 years ago
-
Hi,
Thanks you for the very interesting library! Looking at the code I was wondering how you were balancing the different losses scales. The MSE loss is probably on a completely different scale th…
-
-
请问语义分割标签是24类吗，下面的cls对应的是每个模型对应的面及其特征吗，为啥这里有“10”：26。我想具体了解一下每个标签对应的实际特征是什么，麻烦了。
{"cls": {"0": 24, "1": 23, "2": 9, "3": 24, "4": 10, "5": 24, "6": 9, "7": 24, "8": 21, "9": 24, "10": 26, "11": 24, "12…
-
Hello, could you please explain how your multi-teacher model method conducts experiments with PODNet and AFC? It seems that this is not clearly indicated in your code.