-
```python
LightXML/apex$ pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
WARNING: Disabling all use of wheels due to the use of …
-
Hi ! I ran the command mod.train(max_epochs=250, use_gpu=True) using the recommended
dataset (V1_Human_Lymph_Node) on M3 MacBook Pro and I got this error:
```
[/opt/anaconda3/envs/cell2loc/lib/py…
-
(spacetimeformer) adewdev@bootedeagle:~/Devtools/PyWS0/spacetimeformer-main-original/spacetimeformer$ python train.py spacetimeformer solar_energy --context_points 168 --target_points 24 --d_model 100…
-
I'm very new to this library and the first question I have in mind (you may find it trivial): is there any flexible way to extend the list of features from https://github.com/mahmoud/ashes#compatibili…
-
The epsilon value of 1e-12 used in the following lines for the `first_step` and `sam_train_step` functions is too low and can cause NaN errors with training with mixed precision:
`e_w = gradients[i] …
-
I was trying to train a mobilenet model using arcloss on casia dataset and I am unable to exceed lfw acc more than ~0.9763.
I wanna know is this the best accuracy I can get using this dataset(casi…
-
Does **amp** support PyTorch **1.0.0**? Or shall I rather use the FP16_Optimizer? As far as my what I have understood, amp is a more advanced version of FP16_Optimizer which performs unsafe ops in FP3…
-
When I run the tutorial [Example: Deep structural causal model counterfactuals](https://basisresearch.github.io/chirho/deepscm.html), the following cell:
```Python
adam_params = {"lr": 1e-3}
batch_…
-
### Bug description
The checkpoint callback is run before ```batch_progress.increment_completed()``` in training_epoch_loop's ```advance``` method. Thus in the checkpoint
checkpoint['loops']['fit…
-
Hi, I'm getting an error when I try to get the grad-cam visualizations for a custom model with two inputs. A minimal working example follows
```
img_width=224
img_height=224
model = EfficientN…