-
Sharing parameters [adds a function](https://github.com/torch/nn/blob/82c76d450336fc1f3e0a582ef49d80c117714ec0/Module.lua#L98-L99) on the table, for both instances. If one does not care and save the m…
-
### 🐛 Describe the bug
I would like to raise a concern about the spectral_norm parameterization.
I strongly believe that Spectral-Normalization Parameterization introduced several versions ago do…
-
supervised
unsupervised
classification problem
linear regression problem
logistic regression problem
squared loss
mean square error(MSE): average squared loss per example over the whole dat…
-
Hi,
After making some tries with classic presence/pseudo-absences datasets, I am trying to fit some models using a presence-only dataset. However, when using this option I get always strange outputs …
-
## ❓ Questions and Help
Hi, I'm using Theseus to do pose graph optimization, and I I encountered two problems:
1. Every time I try to run optimization, system memory usage sharply exceeds 50 Gb, alt…
-
Are there any plans to support bf16 training in deepspeed in the near future?
If not - could someone guide me toward what I would need to change in order to implement it? It seems like a fair few thi…
-
I am testing the 1.3B training. Steps 1 and 2 have already passed, but there is no change in reward after completing step 3.
I used LoRa to train for one iteration, and the results of steps 1 and 2…
-
Processing 3.3.6
Mac OSX 10.12.6
noSmooth does not work with P2D or P3D.
```java
PGraphics pg;
void setup() {
size(640, 640, P2D);
noSmooth();
pg = createGraphics(32, 32);
…
-
I discovered via issue NLPbox/stagedp-service#1 that NeuralEDUSeg crashes on some, mostly very short, input sentences:
```
$ cat /tmp/bad_input.txt …
-
I am trying to reproduce the results of the CMU Motion Capture dataset. I use references from examples/latent_sde_lorenz.py, the paper, and the preprocessed dataset [linked by ODE2VAE's repo](https://…