-
Hey,
Is it sufficient to have the spectograms in half precision format (float16)? And did you train your model with mixed precision?
-
**Is your feature request related to a problem? Please describe.**
The ORM was edited a lot over the years and is unbearable anymore. Every few weeks, new bugs are discovered. Some are ground breakin…
-
Hello,
I am using Pytorch3D to create my dataset for training a neural network. As you know the tensors in Pytorch3D have the type of torch.float32. On the other hand, Pytorch_Lightning has the mixe…
-
**System information**.
- Have I written custom code (as opposed to using a stock example script provided in Keras): Yes
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Colab
- TensorFlo…
-
Hello,
thank you very much for sharing this great work.
Unfortunately I am unable to reproduce the paper's results for Sintel-test.
I trained the network using train_mixed.sh. For Sintel-test, the …
az-ja updated
3 years ago
-
I am not really shure whether I do / understand something wrong but I get very inconsistent results from `powerSim()` when using `extend()`. I do the following:
```
# Import data set of 5 particip…
-
Thanks for your contribution, it is a great work, how to fintune my dataset? like mural dataset, can you give the command or script?
-
_This MSc student research task may or may not end-up with actual code submitted into this repository_
Main Goal: **Exploration of applicability of explainable artificial intelligence technique for…
-
--Example 1: semi-colon in middle of "5= AGE>; 85"
1= .z < AGE
-
Hello,
Have you trained MixNet models for Cifar-10 from scratch (not transfer learning from ImageNet models)?
With default configuration, I obtain about 70% accuracy for MixNet small, and the ac…