-
Input code
```python
# Create mask for np.nan values
tensor_mask = ~np.isnan(tensor)
# Set nans to 0 otherwise loss is always nan
tensor[~tensor_mask] = 0
# Create tensor, set device to …
ckmah updated
3 years ago
-
请问将文内引文格式设定为bib-style = author-year后，文内引用(\citet{}或者\citep{})的人名和年份之间出现很大的空格，这个问题能够帮忙看下吗
-
**System information**
- TensorFlow version (you are using): 2b1
- Are you willing to contribute it (Yes/No): I want to but I don't think I'm qualified
**Describe the feature and the current beha…
-
Trying to build Tensorflow from a6f856b2f7920d4f74d7ca4e71967258423cc9f0 with CUDA and just started running into this issue:
```
____[7,182 / 7,674] Compiling tensorflow/core/graph/node_builder.cc…
tycho updated
2 years ago
-
Our logp's include normalization terms which are unnecessary for sampling as that is fine with an unnormalized logp. As such, we can optimize the model logp evaluation if we take the Theano computatio…
-
Hello,
As part of a project, I am trying to fix up some things with [automlbenchmark](https://github.com/openml/automlbenchmark) and from there realized oboe does not install correctly.
### Repr…
-
I'm just attempting to get started using pyro, and was trying to work through examples when I found that the example listed on the example page under "Multivariate Forecasting" reliably fails for me.
…
-
This ticket implements:
- Support for full subcategories defined by an axiom (Finite,
Infinite, Facade, Commutative, Associative, Unital, Inverse,
Distributive, NoZeroDivisors, Division, Finite…
-
## CPU Rules
- [x] Multi-level-tiling
- [x] Multi-level-tiling-with-fusion
- [x] Factorize-reduction
- [ ] Simplify-compute-with-const-tensor
- [x] Add-cache-write
- [x] Always-inline
- [x] Par…
-
This issue is about recent developments in the OT literature that have been concerned with scaling for
- entr. reg. OT
- GW
- FGW
We can collect some results here and note down methods that we …