FeiYull

YOLOV8 model deployment(TensorRT + CUDA C)

4

### Description yolov8 andyolov5 are very powerful object detection algorithm in my heart. Here I give the model deployment of yolov5 and yolov8. The method is: cuda c and tensorrt,...

warning:[E] [TRT] 3: [runtime.cpp::~Runtime::346] Error Code 3: API Usage Error (Parameter check failed at: runtime/rt/runtime.cpp::~Runtime::346, condition: mEngineCounter.use_count() == 1. Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior.

3

warning:[E] [TRT] 3: [runtime.cpp::~Runtime::346] Error Code 3: API Usage Error (Parameter check failed at: runtime/rt/runtime.cpp::~Runtime::346, condition: mEngineCounter.use_count() == 1. Destroying a runtime before destroying deserialized engines created by the runtime...

reference: https://blog.csdn.net/ayxc_ve/article/details/134174176

reference: https://blog.csdn.net/m0_72734364/article/details/133901479

how to train with tiny checkpoints?

3

i have done the following changes: 1. https://github.com/WZH0120/SAM2-UNet/blob/eb1c38d870358cbdd769c9721062f7bb888ef9b5/train.py#L15 2. edit the yaml https://github.com/WZH0120/SAM2-UNet/blob/eb1c38d870358cbdd769c9721062f7bb888ef9b5/SAM2UNet.py#L127 but errors occur like python3.9/site-packages/torch/nn/modules/module.py", line 2215, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError:...