-
Can I deploy the pre training model of "segocr simple baseline." to C + +, such as libtorch, but because of your good encapsulation, I can't simply restore the network structure, so I can't convert. T…
-
### 🐛 Describe the bug
Reproduce:
```python
import torch
class Model(torch.nn.Module):
def __init__(self):
super().__init__()
self.bias = torch.nn.Parameter(torch.zero…
-
Currently this package on Android goes from Dart to Java via message channels, then from Java to C++ glue code via JNI, then from that C++ to the actual core pytorch library (and then all the way back…
Hixie updated
10 months ago
-
### 🐛 Describe the bug
Building a non-trivial extension with cmake currently runs into several problems that need to be worked around:
1) Requesting the Torch package from cmake messes up the cuda a…
ngc92 updated
9 months ago
-
### 🐛 Describe the bug
Hello!
I want to use libtorch's c++ api for algorithm inference, but currently the c++ version in my project only supports c++11, corresponding to gcc 4.8.5 and g++ 4.8.5, ca…
-
I'm getting the error below when running any torch code. This is probably due to an incompatible cuda version (requirements.txt specifies cu121).
I would suggest to
- ether add a comment in `REAM…
-
### Your current environment
```text
PyTorch version: 2.3.0a0+ebedce2
Is debug build: False
CUDA used to build PyTorch: 12.3
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.3 LTS (x86_64)
…
-
### 🐛 Describe the bug
Hi everyone,
I am trying to use `DistributedRandomSampler` in the C++ frontend. However, it is not behaving as I would expect: it uses the same random order of examples in e…
-
Can you please update the tch version? I cant be build using the latest libtorch.
Do you have a plan to support yolov8?
Thanks for your work. :)
-
## 🐛 Bug
I have already asked questions in the forum, the link is as follows,
https://discuss.pytorch.org/t/why-same-model-in-cuda-and-cpu-got-different-result/56241
I happened in the same prog…