-
There are so many hypothesis configs for this test that it may take several tries before this error appears. Or you can increase the robustness of the test with `@hypothesis.settings(max_examples=50)`…
-
This problem for me occurs very randomly. The network (in this case Retinanet) is training just fine, when at a random number of iterations `context_gpu.cu` fires up and seems to eat up the gpu memory…
-
## Issue description
libtorch is using `miniz` via `caffe2`. The final `.so` exports all those symbols which leads to problems in programs using other libraries using `miniz`, too.
Please disabl…
-
## 🐛 Bug
Building torch results in
```
torch/csrc/distributed/c10d/ProcessGroupMPI.cpp:131:10: error: no member named 'cerr' in namespace 'std'
```
## To Reproduce
Steps to reproduce th…
-
## 🐛 Bug
With Visual Studio 2019, build from source (directly invoke CMakeLists) with `USE_VULKAN ON` (and `USE_VULKAN_SHADERC_RUNTIME ON`) fails due to usage of C++20 features in libtorch sour…
-
Got the error during running the train.py file:
Transferred 308/361 items from yolov5s.pt
Scaled weight_decay = 0.0005
optimizer: Adam with parameter groups 59 weight (no decay), 62 weight, 62…
-
Hi, I'm building the framework on Ubuntu 14.04 using CUDA 7.5, A compilation error occurs.
[ 18%] Building NVCC (Device) object third_party/gloo/gloo/CMakeFiles/gloo_cuda.dir/gloo_cuda_generated_cu…
-
Hi,
i am using this [https://github.com/leonardvandriel/caffe2_models](url) pretrained ResNet-Model and i am trying to get it to work with bigger pictures (FullHD), but i couldn't find anyway to re…
-
Hi!
I've been experimenting with Caffe2. I could convert original Caffe models that we have ([net.deploy.prototxt, net.deploy.caffemodel] -> [net.init.pb, net.deploy.pb]) and run them (train) in a s…
-
### 🐛 Describe the bug
Trying to build the latest version of libtorch to use it in a c++ project.
```
cmake -D BUILD_SHARED_LIBS=ON -D CMAKE_BUILD_TYPE=Release -D USE_CUDA=ON -D USE_CUDNN=ON -D …