Initial commit: DCNv4 custom op mirror setup
- Add enhanced README with project structure and quick start guide - Initialize repository with DCNv4 CUDA extension (PyTorch module) - Include classification, detection, and segmentation subdirectories - Reference upstream OpenGVLab DCNv4 implementation Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
2
segmentation/deploy/configs/_base_/backends/tensorrt.py
Normal file
2
segmentation/deploy/configs/_base_/backends/tensorrt.py
Normal file
@@ -0,0 +1,2 @@
|
||||
backend_config = dict(
|
||||
type='tensorrt', common_config=dict(fp16_mode=False, max_workspace_size=0))
|
||||
Reference in New Issue
Block a user