-
Dear all,
It seems that `torchbearer` does not want to work for me. I am trying to simply classify images using resnet. You can find my code here (https://github.com/FrancescoSaverioZuppichini/PyTo…
-
## 🐛 Bug
Thank you for the great library! When migrating a larger project, I am running into memory issues, though, so maybe someone can help me out.
So, I have a pretty complicated DataSet whic…
-
Dear all,
first of all, I love this library.
The `ReduceLROnPlateau` is not working when I call `trail.evaluate`.
```python
...
trial = Trial(cnn, optimizer, loss, metrics=['acc', 'los…
-
Hi Guys,
`EarlyStopping` has the same problem we had with #650 . Basically, when we evaluate everything will explode because `val_loss` does not exist.
```python
trial = Trial(cnn, optimiz…
-
-
Hi all,
Currently, i'm looking for high level library that can help me to simplify my Pytorch's training code. After some searches, i found these libraries are promising to try: Ignite, TNT, and To…
-
## 🚀 Feature
Simplified API, with callbacks... as e.g. Keras did, pass just list of callbacks to be executed and Trainer will call then when needed instead of having them specified
https://github.…
Borda updated
4 years ago
-
When using data parrallel, torchbearer tries to pass state and catches TypeError if this fails. Data parrallel throws a different error
-
I get this as output, in history tutorial, in colab, should this be something different?
HBox(children=(IntProgress(value=0, description='18/20(t)', max=1), HTML(value='')))
-
hello sir! I tried to run your code,but there are some bug and do not know how to solve,here are the Traceback :
MNIST:
File "/home/sdc/Desktop/STAWM-master/mnist_class_28.py", line 121, in
…