-
I turned on `torch.autograd.set_detect_anomaly` and found that nan loss happened during backward calculation of smooth_l1_loss:
```
rois_label, adja_loss, adjr_loss = fasterRCNN(im_data, im_info, …
-
/home/bridgei2i/.local/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: libtorch_cuda_cu.so: cannot open shared object file: No such file or…
-
when I run the code, it tells me that
File "/usr/local/lib/python3.5/dist-packages/torch/autograd/function.py", line 180, in backward
raise NotImplementedError
NotImplementedError
-
I am trying to back-propagate a custom gradient tensor through the FlowNet2 model. I know that this is possible in PyTorch using the following methodology:
```
model = Net()
model = torch.load('.…
-
If there are distributed operations like `dist.all_reduce` in the model, the aot autograd can't make graph properly.
How can we solve this?
-
I always failed to install the gsplat.
So I transfer other people's conda environment to run the gsplat, but it takes this error:
```
Traceback (most recent call last):
File "test.py", line 17, …
-
When I run
`./train_ycb.sh`
contents of train_ycb.sh
> #!/bin/bash
> n_gpu=1 # number of gpu to use
> python3 -m torch.distributed.launch --nproc_per_node=$n_gpu train_ycb.py --gpus=$n_gpu
…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports.
…
-
Хочу дообучить номера подскажите какой скрипт отвечает за выдерание номеров из картинок?
На хабре нашел инструкцию но она устарела =(
-
作者您好,我仿照`roi pool`中的gradcheck.py脚本写了一个可形变卷积的梯度检查代码,可变形卷积的前向结果是可以输出的,但是在进行到gradcheck()函数部分,却提示我说需要分配40000.00 GiB的内存到GPU上,然后报显存不足的错误,下面是我的代码,想问一下出现上述问题的原因,是我写的代码的问题呢?还是源码的问题呢?
```
import os.path as …
HsLOL updated
2 years ago