-
#### Summary:
The covariance estimation currently used to construct a dense mass matrix is yielding sufficiently poor results that the resulting chains go crazy.
#### Description:
It looks like the…
-
How is the PyTorch model trained? What parameters are used (especially regularization)?
The README suggests that the DeepMushroom repo is used, however that is fast.ai- rather than pytorch-based, a…
-
I started using the multivariate rank-1 CSC, and am unsure about how to select the parameters, e.g. the regularization and number of atoms. Which output should I look at to assess the fit independentl…
-
full parameter update里面，我最近在试一种新的loss function，就是在原有的next token prediction上面加一个regularized term，希望某些layer的weights能尽可能小。可是总会遇到一些奇怪的bug。下面是我加的代码和遇到的error：
比如在lomo_trainer.py中：
```python
lamda, regu…
-
Within MultiSeg Parameter Files, the section Registration-parameters-DTI is nonrecognizable for loading and isn't correctly saved:
\
\
\
\
\
\
\
…
-
Hi! Similar to #15 I get very poor results on my own dataset as soon as the depth distortion loss and normal loss kicks in (iteration 15k), it just gets extremely blurry. I tried adjusting the lambda…
-
Hello
Thanks for this nice software.
I have a pdf file that explains the local algorithm, but is there a pdf file that explains the global algorithm?
Sorry for my inconvenience in English.
-
Hi
-
In TensorFlow 1.x, or similar computation graph based deep learning framework, we could serialize the model into a protobuf file. And then, we can split the file into two parts, one for worker, the ot…
-
I have a number of regularization parameters in sweeps that I run that I would like to sample from a log-uniform distribution, but also include 0 as a possible value. For example, see Appendix B of "T…