-
## 🚀 Feature
Currently you cannot use digits in names of tensors. Please allow digits, so that `torch.randn(64, 64, 4, 4, names=("height", "width", "channel_0", "channel_1"))` works rather than thr…
-
Steps to reproduce the issue:
```
git clone https://github.com/taesungp/contrastive-unpaired-translation CUT
cd CUT
conda env create -f environment.yml
conda activate contrastive-unpaired-transla…
-
Hi Mark,
i wonder where the dataset comes from.
Is it an open-sourced dataset published by an institution? If yes, would you tell its origin paper?
Or is it produced by yourself?
thank you~
-
This email: [pylearn-users] Neural tensor network
give an implentation to of a neural tensor layer (Socher et al. 2013) here:
https://gist.github.com/minhlab/9f4109dcdb66b2ce6358
Socher, R., Chen, …
nouiz updated
9 years ago
-
Got the following error in the second to last line of `loglike_sums()` within `torch_mle()`
```RuntimeError: The size of tensor a (1420) must match the size of tensor b (1421) at non-singleton dimens…
-
You may already have noticed it, and I'm just commenting that the code could be sped up substantially if we simplify the expression by applying an inequality and telescoping. You should also check you…
-
I have two environments to collect and evaluate trajectories. The `action_tensor_spec` is the following:
```
BoundedTensorSpec(shape=(5,), dtype=tf.float32, name='action', minimum=array(-0.2, dtype=…
b-fg updated
9 months ago
-
Firstly, I wanted to thank you for the great project, it helped me understand Recurrent PPO better.
I mostly have one main question, regarding how the training is done, especially regarding the Act…
-
Hello! I've been using Julia quite a bit for theoretical physics simulations. In particular, I do a lot of work with tensor networks, which are networks of tensors that must be contracted to compute a…
-
Hi G,
I am so new to Torch, just a quick concern about fetching training data. The training data is supposed to be normalized, too. However, I see no such operation in the `dataTrain:getBatch()` call.…