-
Before filing an issue, please make sure to tick the following boxes.
- [x] Make sure your issue hasn't been filed already. Use GitHub search or manually check the [existing issues](https://github.…
-
Currently we have SGD and Adam. Should be relatively simple to add more, like RMSProp, etc. Some references:
- http://cs231n.github.io/neural-networks-3/#update
- https://github.com/Lasagne/Lasagne/bl…
-
As per the readme file, I have changed some values in the arguments to make the model easier to train. Since, I have only one gpu, I have change num_process_per_node to 1.
But I am getting this er…
-
Hi,
I am trying to run NVAE on my machine with your command line for CIFAR10 (updating only the .. from 8 to 4 cause I own 4 GPUs):
```
export EXPR_ID=/home/dsi/eyalbetzalel/NVAE/logs
export…
-
Currently, `torch.optim` optimizers in PyTorch C++ API behave slightly differently from the Python API. In order to achieve parity, we should check the following aspects of an optimizer:
1. Make su…
yf225 updated
4 years ago
-
After some fixes to the summary & split calls (i.e. they were refactored in tf1.0) I still can't get this code to work:
```bash
(.venv) ➜ iaf git:(master) ✗ CIFAR10_PATH="./CIFAR10" optirun -b prim…
-
I have some trouble reproducing the baseline results with RN and UpDn on CLEVR. Can you share the scripts for reproducing the baseline results (RN, UpDn, etc.) with the precise hyperparameters used (b…
-
Hi, I am trying to train the tractseg model with my own data. But after training the third model (TOM one), the loss was getting minus. Here is the hyperparameter I used:
{'BATCH_NORM': False,
'BAT…
-
Using gpu device 0: GeForce GTX 980 (CNMeM is enabled with initial size: 80.0% of memory, cuDNN 5105)
/home/vismod/anaconda2/envs/tensorflow/lib/python2.7/site-packages/theano/sandbox/cuda/__init__.p…
-
#### Ajustar os seguintes parâmetros
- Regularização (L1, L2, Dropout, Clipping);
- Early Stopping;
- Taxa de aprendizagem (lr);
- Funções de ativação (testar a softsign no lugar da tanh);
- Ot…