-
Hello Jong Wook,
I would like to experiment fine-tuning Onsets and Frames on a custom dataset with your PyTorch implementation.
For that I would ask, is there a pretrained model checkpoint avail…
-
### 🐛 Describe the bug
When using `torch.distributed._state_dict_utils._broadcast_tensors`, it is possible for tensors which need to be broadcasted to live on the CPU (such as with a CPU offloaded …
-
Hello,
One of the main use cases when deploying real-world models is to train several "expert models" on different subtasks of the main inference task, then using some linear combination of them to…
-
I tried to cluster 3,974,973 objects (with 32 features). After some days, the calculation was canceled with the following error:
```
Fatal Python error: Cannot recover from stack overflow.
Curr…
moi90 updated
6 years ago
-
### 🚀 The feature, motivation and pitch
Currently, we check view consistency by checking if `a._is_view` and `b._is_view` are both correct: https://github.com/pytorch/pytorch/blob/master/test/test_op…
-
## 🚀 Feature
Add PlackettLuce and RelaxedPlackettLuce distributions. It is a simple distribution over permutations.
## Motivation
For optimization over categorical/binary variables (i.e. variat…
-
Hi, thank you for your code. It is the pytorch implementation of the paper SIGVAE. However, the results I obtained by running the code you provided are too far from the experimental results in the pap…
-
Hi, I'm wondering if your segcaps implementation in pytorch for segmentation task can work?
I also do some research about segmentation and want to test SegCaps performance in our dataset
-
### 🐛 Describe the bug
`torch.nn.functional.binary_cross_entropy` crashes when the values have singleton dimensions. This error cannot be caught.
Sample code:
```python
import torch
import torc…
-
Many thanks for making this PyTorch implementation available. The pre-processed Human3.6M dataset and the pre-trained model on Google Drive look not available anymore, can you please re-upload them? T…