-
### Is your feature request related to a problem? Please describe.
As pointed out recently in other places, some (me) might say our focus system is horribly out of whack, and a way to improve our s…
-
After reading the sample in http://caffe.berkeleyvision.org/tutorial/layers.html, I know 'lr_mult' is learning rate multipliers for the weights or the biases. But there are 3 'lr_mult' in deep_lstm_sh…
-
I'm f'tuning MDNet to my data. Only the first frame in the video is labelled with a bbox. After 8-10 frames the target score drop below 0. I played with learning rates/multipliers/trainable layers, bu…
-
Hi,
I am trying to reproduce the experiments in ["Differentially Private Learning with Adaptive Clipping" (2021)](https://arxiv.org/abs/1905.03871), the source code for which is provided under `fed…
-
Is there any Tensorflow Probability-based implementation of the uncertainty based change in learning rates, that uses Flipout layers?
-
Hi, thank you so much for open-sourcing this amazing repo!!
I was trying to run a simple training on the conditioned diffusion model with 1710 of 3-minute audio tracks, but I noticed that even aft…
-
Recently I made an issue about this problem and now it's closed depends on 2.13. release. So, I've installed this release from steam workshop and problem with multiplier still here. Maybe it also depe…
-
I created a simplest net to learn the division "/" function (input is A and B, label is A/B). However, when I try to run the trainer, it hang forever. If I do `killall caffe`, I see that it's waiting …
-
**Bug Discription & To Reproduce**
The source code is from current main branch, and follow the instructions in the `README-MUP.md` until this step:
![image](https://github.com/EleutherAI/gpt-neox/as…
-
I train my model on Ubuntu 16.04 with the command below:
`darknet detector train darknet19_448.conv.23 | tee log.txt`
Here is my learning rate strategy in the cfg_file:
```
learning_rate=0.000…