dotnet / dotnet/machinelearning-modelbuilder
Text classification cancel hangs - Reopening mbconfig shows no compatible GPU
- Dominant language
- Dockerfile
- Stars
- 285
- Forks
- 66
- PR merge metrics
- No merged PRs in 30d
Description
**System Information (please complete the following information):**
- Model Builder Version (available in Manage Extensions dialog): 16.14.0.2255703
- Visual Studio Version: 17.3.6
**Describe the bug**
- On which step of the process did you run into an issue: Environment and Train
- Clear description of the problem:
For the text classification scenario, when I cancel training, it hangs and the the process never seems to finish. Closing the .mbconfig file and opening it again shows that the there is no compatible GPU, even though I do have a compatible GPU.
**To Reproduce**
Steps to reproduce the behavior: Train a text classification GPU on a Local GPU environment.
**Expected behavior**
Training cancels successfully and reopening mbconfig shows my GPU.
**Screenshots**

**Additional context**
Log from cancelled training:
[TextClassification-ELQVV5.txt](https://github.com/dotnet/machinelearning-modelbuilder/files/9956318/TextClassification-ELQVV5.txt)
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.